© 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. 15979
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to court cases

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

    legal document headers and formal citation formats.

    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
    ContentAlignment
    -0.49
    脚注の使い方
    -0.44
    ----</
    -0.43
    jamientos
    -0.41
     BoxFit
    -0.39
    ">//
    -0.39
    xrLabel
    -0.38
    يكب
    -0.38
    ])):
    -0.36
    行政区划
    -0.36
    POSITIVE LOGITS
     NJ
    1.39
    NJ
    1.27
     Jersey
    1.26
    Jersey
    1.14
     JERSEY
    1.09
     nj
    1.08
     Newark
    1.04
     Rutgers
    1.03
    nj
    0.98
     Nj
    0.91
    Activations Density 0.410%

    No Known Activations