© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 4995
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to biological processes and mechanisms

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

    technical and scientific terminology related to complex systems and measurements.

    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
     للاسماء
    -0.75
    LookAnd
    -0.68
     Biôgrafia
    -0.59
    thâu
    -0.59
    ьаж
    -0.56
    optionalTypeArgs
    -0.54
    jface
    -0.52
    windowFixed
    -0.51
     Италијани
    -0.49
     Wikimedijinoj
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.68
    Tembelea
    0.50
     CURIAM
    0.48
    ValueGeneration
    0.47
    học
    0.46
    IntoConstraints
    0.45
    ])),
    0.44
     سكانية
    0.44
    */}
    0.43
    getSupport
    0.42
    Activations Density 17.638%

    No Known Activations