© 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. 9-GEMMASCOPE-RES-16K
    11. 1734
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance measurement and evaluation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WEBPACK
    -0.53
    InputChange
    -0.47
    ablecer
    -0.45
    anet
    -0.45
     eye
    -0.45
    ero
    -0.44
    ően
    -0.44
    __*/
    -0.44
    术
    -0.44
    zulegen
    -0.44
    POSITIVE LOGITS
    isContained
    0.74
     myſelf
    0.74
     pleaſure
    0.74
     ciasc
    0.72
    IntoConstraints
    0.71
     ainfi
    0.69
     moschino
    0.68
     strtotime
    0.68
    منم
    0.67
     responsabilità
    0.67
    Activations Density 1.352%

    No Known Activations