© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9328
    Prev
    Next
    INDEX
    Explanations

    references to grandchildren and toys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WireFormatLite
    -0.48
    ombie
    -0.46
    OrEmpty
    -0.46
     germain
    -0.44
    duff
    -0.44
    mism
    -0.43
    labelControl
    -0.41
     emi
    -0.41
     TokenType
    -0.41
    matica
    -0.41
    POSITIVE LOGITS
     grandchildren
    0.79
     nieces
    0.73
     Toys
    0.65
     toys
    0.60
    Toys
    0.59
     grandsons
    0.57
     singles
    0.57
     grandson
    0.56
    grandchildren
    0.54
     lay
    0.53
    Activations Density 0.234%

    No Known Activations