© 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. 15701
    Prev
    Next
    INDEX
    Explanations

    dates expressed in the format month and day

    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
    ViewInit
    -0.73
     CMP
    -0.70
    deepcopy
    -0.69
     newName
    -0.69
    ："
    -0.68
     Mercu
    -0.67
    pruch
    -0.66
    smith
    -0.65
     SNS
    -0.65
    CharField
    -0.64
    POSITIVE LOGITS
     October
    1.88
    October
    1.76
     OCTOBER
    1.54
     Oktober
    1.53
    OCTOBER
    1.51
     oktober
    1.43
    Oct
    1.42
     Oct
    1.41
     october
    1.39
     octubre
    1.32
    Activations Density 0.116%

    No Known Activations