© 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. 15-GEMMASCOPE-RES-16K
    6. 13110
    Prev
    Next
    INDEX
    Explanations

    instructional phrases guiding actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.67
    Портал
    -0.59
    usstsein
    -0.58
     nguyễn
    -0.55
     pylint
    -0.54
    __).
    -0.54
    RemoteException
    -0.53
    thenReturn
    -0.53
     ")");
    -0.52
     ligiloj
    -0.52
    POSITIVE LOGITS
     To
    0.87
    To
    0.87
     Чтобы
    0.70
    volo
    0.60
     Whom
    0.59
     TO
    0.58
    Чтобы
    0.56
     estimés
    0.56
    peka
    0.55
    Для
    0.55
    Activations Density 0.110%

    No Known Activations