© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12068
    Prev
    Next
    INDEX
    Explanations

    information related to plans for renovations and changes in a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    structured informational content about plans, renovations, and institutional announcements with detailed descriptions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IMHO
    -0.86
     :-)
    -0.78
     ;-)
    -0.78
    IMHO
    -0.75
    :-)
    -0.73
     OTO
    -0.72
    ;-)
    -0.72
     Надо
    -0.70
     BTW
    -0.70
    クルマ
    -0.69
    POSITIVE LOGITS
     lecz
    0.74
    看见
    0.60
    NumOf
    0.59
     solely
    0.55
     endast
    0.55
     possu
    0.55
    听见
    0.54
    casted
    0.54
     sodass
    0.54
     riguardo
    0.54
    Activations Density 1.470%

    No Known Activations