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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8797
    Prev
    Next
    INDEX
    Explanations

    phrases related to the presence or absence of permissions and limitations

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

    French language followed by "pas"

    np_acts-logits-general · gemini-2.0-flash

    ne fonctionne pas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    absl
    -0.54
    wenn
    -0.52
     endblock
    -0.50
     Maguire
    -0.49
    protocols
    -0.46
    gså
    -0.46
     Daphne
    -0.45
    Inclusion
    -0.45
     Thad
    -0.45
    cstdio
    -0.45
    POSITIVE LOGITS
     الرياضيه
    0.95
    /**
    0.79
    ConstraintMaker
    0.77
     resourceCulture
    0.70
    脚注の使い方
    0.68
    makeConstraints
    0.67
    BorderFactory
    0.66
    Autoritní
    0.66
    原始内容存档于
    0.66
     CreateTagHelper
    0.65
    Activations Density 0.051%

    No Known Activations