© 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. 8980
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts associated with court cases and evidence

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

    phrases indicating that something should be considered as evidence along with other factors in legal or evaluative contexts.

    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
     吋
    -0.46
    \{\\
    -0.46
    kungen
    -0.43
    
    -0.43
    лтемелер
    -0.41
     Meksiku
    -0.40
    contentLoaded
    -0.39
    ͋
    -0.39
    DBNull
    -0.39
     kaarangay
    -0.39
    POSITIVE LOGITS
     junto
    2.97
     alongside
    2.81
     juntamente
    2.56
     along
    2.55
     together
    2.47
    along
    2.45
     вместе
    2.39
    junto
    2.33
    together
    2.28
     Junto
    2.23
    Activations Density 2.069%

    No Known Activations