© 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. 6618
    Prev
    Next
    INDEX
    Explanations

    terms related to interactions and state changes within coding and programming contexts

    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
    GPC
    -0.59
    Organisateur
    -0.54
    бири
    -0.52
     textStatus
    -0.50
     UserRepository
    -0.48
     useHistory
    -0.48
    IgnoreCase
    -0.48
    athione
    -0.46
     Heng
    -0.46
     ego
    -0.46
    POSITIVE LOGITS
     متعلقه
    0.64
     Reap
    0.63
     OnTriggerEnter
    0.59
     Roskov
    0.58
    mapStateToProps
    0.57
    rrggbb
    0.57
    {/
    0.55
    lardır
    0.55
    AsUp
    0.55
     {?
    0.55
    Activations Density 0.274%

    No Known Activations