© 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. 11-GEMMASCOPE-RES-16K
    6. 8629
    Prev
    Next
    INDEX
    Explanations

    words related to the identification and classification of subjects or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecake
    -0.61
    Corollary
    -0.61
     roost
    -0.61
    httphttps
    -0.60
    coaster
    -0.60
    charts
    -0.59
     htons
    -0.58
    Kjelder
    -0.58
    々
    -0.57
     poko
    -0.57
    POSITIVE LOGITS
    identi
    1.29
    Identi
    1.28
     Identi
    1.24
     identifies
    1.22
     Identified
    1.21
     Identities
    1.20
     identifying
    1.19
     Identify
    1.17
     identifiable
    1.14
     identifica
    1.13
    Activations Density 0.099%

    No Known Activations