© 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. 10-GEMMASCOPE-RES-16K
    11. 12416
    Prev
    Next
    INDEX
    Explanations

    demographic data and statistical representations of racial and ethnic diversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     solaire
    -0.55
     Parigi
    -0.47
     rurale
    -0.47
     popolare
    -0.46
     soldat
    -0.44
     volontaire
    -0.43
     malade
    -0.43
     riêng
    -0.43
     auroit
    -0.42
     polaire
    -0.41
    POSITIVE LOGITS
    AnchorStyles
    0.87
    SharedDtor
    0.79
    OrBuilder
    0.74
    EDEFAULT
    0.71
    minecraftforge
    0.67
    StoryboardSegue
    0.65
    MemoryWarning
    0.65
    SPATH
    0.65
     ProtoMessage
    0.63
    HasForeignKey
    0.62
    Activations Density 0.630%

    No Known Activations