© 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. 38-GEMMASCOPE-RES-16K
    6. 13453
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Tim" along with variations and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEncoder
    -0.54
    󠁮
    -0.48
    laway
    -0.44
    fillType
    -0.43
     dAtA
    -0.43
    nextNode
    -0.42
    省市镇
    -0.42
    lassung
    -0.42
     Nucleus
    -0.42
     Destroyer
    -0.40
    POSITIVE LOGITS
    Tim
    0.69
     Tim
    0.68
     tim
    0.56
     TIM
    0.55
    tim
    0.48
    TIM
    0.46
    Timo
    0.41
    timb
    0.41
    othe
    0.40
    Tam
    0.40
    Activations Density 0.343%

    No Known Activations