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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4216
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and specific numerical formats or codes

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

    hexadecimal memory addresses and numeric values in debug logs and system data.

    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
    bootstrapcdn
    -0.44
     novia
    -0.35
     enver
    -0.31
    案
    -0.31
    клопе
    -0.31
     đại
    -0.31
    trás
    -0.31
    dcterms
    -0.30
    eseorang
    -0.30
     cotidiana
    -0.30
    POSITIVE LOGITS
    يميديا
    0.69
     $:$
    0.65
     $:
    0.64
    Autoritní
    0.64
    []):
    0.63
    {}",
    0.61
    {}'.
    0.59
    _:
    0.59
    <%@
    0.59
    __:
    0.58
    Activations Density 0.795%

    No Known Activations