© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 7128
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty and contradiction in opinions or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressions of strong affirmation or negation, especially emphatic interjections or decisive yes/no responses.

    oai_token-act-pair · gpt-5Triggered by @areeb0102

    affirmative or negative words.

    oai_token-act-pair · deepseek-r1Triggered by @areeb0102

    emphatic affirmations and strong denials or negations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.85
    Personensuche
    -0.68
    GEBURTS
    -0.65
     "$@"
    -0.57
     invokingState
    -0.52
    }$.\\
    -0.50
    verifyException
    -0.47
    ophthal
    -0.47
    }}$\\
    -0.47
    saraba
    -0.45
    POSITIVE LOGITS
    AxisAlignment
    0.70
    CodeAttribute
    0.68
    Cyfeiriadau
    0.66
     typelib
    0.66
    脚注の使い方
    0.59
    LookAnd
    0.59
    RectangleBorder
    0.59
    nodoc
    0.56
    TagHelpers
    0.55
    printStackTrace
    0.55
    Activations Density 0.221%

    No Known Activations