© 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. 3-GEMMASCOPE-RES-16K
    6. 8508
    Prev
    Next
    INDEX
    Explanations

    phrases indicating recognition or reputation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.61
     reaſon
    -0.61
     abſ
    -0.60
    PostInfinity
    -0.59
     Smarty
    -0.58
     Nguy
    -0.56
    ConstraintMaker
    -0.56
     NIE
    -0.55
     Yat
    -0.54
    intios
    -0.54
    POSITIVE LOGITS
    Bronnen
    0.71
     dikenal
    0.70
     conhecida
    0.68
     kjent
    0.68
     known
    0.67
     conhecido
    0.65
     destacan
    0.64
    Known
    0.62
     conocido
    0.62
     conosciuto
    0.61
    Activations Density 0.179%

    No Known Activations