© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2621
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and their citations

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

    license headers and copyright notices in source code.

    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
     Administrativna
    -0.55
    bootstrapcdn
    -0.50
     استنادى
    -0.44
     snippetHide
    -0.43
    Personendaten
    -0.42
     mergeFrom
    -0.38
    mapStateToProps
    -0.37
    цездатний
    -0.37
    󠁮
    -0.37
    Máy
    -0.36
    POSITIVE LOGITS
     Mo
    0.48
    Mo
    0.46
    Obrázky
    0.44
     mord
    0.42
     stand
    0.42
    Moz
    0.42
     Moz
    0.41
    ValueStyle
    0.41
     mo
    0.41
     Moisés
    0.40
    Activations Density 0.240%

    No Known Activations