© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 91465
    Prev
    Next
    INDEX
    Explanations

    C++ programming language components and syntax

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

    <start_of_turn>user C++ code templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    PyExc
    -0.44
    новништво
    -0.38
    /**
    -0.36
    ьаж
    -0.36
     صوتيه
    -0.34
    __(/*!
    -0.32
    uot
    -0.30
    (['/
    -0.30
     saumon
    -0.30
    voerd
    -0.30
    POSITIVE LOGITS
    ...
    1.27
     ...
    1.20
    …
    1.13
     …
    1.05
    ...",
    1.02
    ....
    1.01
    ...)
    0.99
    ...'
    0.98
    ..."
    0.97
    ...\
    0.97
    Activations Density 0.046%

    No Known Activations