© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 1739
    Prev
    Next
    INDEX
    Explanations

    information regarding processes and conditions that affect overall stability and performance

    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
     Medina
    -0.58
    LookAnd
    -0.56
    niosek
    -0.52
    ringes
    -0.48
    Carriera
    -0.48
    Originally
    -0.47
    isContained
    -0.47
    vian
    -0.47
    SharedDtor
    -0.47
    veland
    -0.46
    POSITIVE LOGITS
    __*/
    0.63
    IVEREF
    0.61
    Know
    0.58
     Know
    0.57
    APORE
    0.57
    xnn
    0.56
    MENAFN
    0.55
     знать
    0.54
     properly
    0.51
    )]=
    0.51
    Activations Density 0.459%

    No Known Activations