© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8899
    Prev
    Next
    INDEX
    Explanations

    conditional statements and their components in the text

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

    conditional clauses introduced by "if".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.58
    adaptiveStyles
    -0.54
     oprot
    -0.51
    NewGuid
    -0.44
    CGRectMake
    -0.43
    bootstrapcdn
    -0.43
     NUKAT
    -0.42
    Tikang
    -0.42
    ime
    -0.42
    TCR
    -0.42
    POSITIVE LOGITS
     there
    0.93
     someone
    0.85
     alguno
    0.77
     somebody
    0.76
    someone
    0.71
    Someone
    0.69
     Someone
    0.68
     někdo
    0.65
     seseorang
    0.60
     ktoś
    0.60
    Activations Density 0.717%

    No Known Activations