© 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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8002
    Prev
    Next
    INDEX
    Explanations

    terms related to accretion and significant terms associated with scientific research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HostException
    -0.73
    ElementException
    -0.72
    ConstraintMaker
    -0.65
     autorytatywna
    -0.61
    خصة
    -0.59
    ransition
    -0.59
    iano
    -0.59
     CURIAM
    -0.58
    itário
    -0.57
    pousada
    -0.57
    POSITIVE LOGITS
     clever
    0.42
     noble
    0.36
    RenderAtEndOf
    0.35
    Clever
    0.35
     stakes
    0.32
     Noble
    0.31
    Portale
    0.31
    })));
    0.30
    Autoritní
    0.30
     toll
    0.30
    Activations Density 0.772%

    No Known Activations