© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6636
    Prev
    Next
    INDEX
    Explanations

    references to "Tam" and related entities in various contexts

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

    starting with "Tam" or "ANT"

    np_acts-logits-general · gemini-2.0-flash

    Tam or cant followed by word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.83
     itſelf
    -0.79
    awtextra
    -0.74
     themſelves
    -0.72
     ſeveral
    -0.70
     auffi
    -0.69
    MLLoader
    -0.67
     becauſe
    -0.66
     himſelf
    -0.65
    addPreferredGap
    -0.65
    POSITIVE LOGITS
    Tam
    0.54
    干
    0.46
     Tam
    0.46
    gradle
    0.43
    hafte
    0.42
    護
    0.42
    TAM
    0.42
    骨
    0.42
    Tak
    0.42
     Helms
    0.41
    Activations Density 0.117%

    No Known Activations