© 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. 4-GEMMASCOPE-RES-16K
    11. 919
    Prev
    Next
    INDEX
    Explanations

    XML parameters related to system components and their configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Попис
    -0.85
    Personensuche
    -0.84
    ']):
    -0.82
    OGND
    -0.80
    IndentedString
    -0.78
     Италијани
    -0.78
    تقاوى
    -0.76
     genoeg
    -0.73
    "]];
    -0.73
    marvin
    -0.73
    POSITIVE LOGITS
    param
    0.97
     param
    0.82
    Param
    0.66
     PARAM
    0.64
     Param
    0.60
     Bioaccumulative
    0.60
    PARAM
    0.60
    typeparam
    0.53
     localObject
    0.51
    ImageField
    0.50
    Activations Density 0.063%

    No Known Activations