© 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. 33-GEMMASCOPE-RES-16K
    6. 55
    Prev
    Next
    INDEX
    Explanations

    quantitative and evaluative phrases related to data analysis and missing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stället
    -0.45
    ContentLoaded
    -0.45
     ProtoMessage
    -0.45
    Autoritní
    -0.42
    +#+
    -0.38
     Wikime
    -0.36
    Datuak
    -0.36
    ství
    -0.35
    stalk
    -0.35
    contentLoaded
    -0.35
    POSITIVE LOGITS
     missing
    3.17
    missing
    2.69
     Missing
    2.58
    Missing
    2.55
     missed
    2.39
     MISSING
    2.31
     miss
    2.23
     misses
    2.17
    MISSING
    1.97
    miss
    1.93
    Activations Density 0.621%

    No Known Activations