Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16171
    Prev
    Next
    INDEX
    Explanations

    references to the name "Tim" or related variations

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

    the name "Tim[othy]"

    np_acts-logits-general · gemini-2.0-flash

    Tim, Timothy, TIM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
    Portail
    -0.47
     שוליים
    -0.46
    EndContext
    -0.41
    MENAFN
    -0.41
    ||}
    -0.41
     []:
    -0.39
    es
    -0.39
    setObject
    -0.38
    MoveNext
    -0.38
    fare
    -0.37
    POSITIVE LOGITS
     Tim
    0.61
    adaptiveStyles
    0.60
    Tim
    0.60
     TIM
    0.59
     tim
    0.51
    🔕
    0.51
    imothy
    0.49
    OTHY
    0.49
    EFIAPI
    0.48
     ✭✭
    0.48
    Activations Density 0.062%

    No Known Activations