© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8935
    Prev
    Next
    INDEX
    Explanations

    names and terms related to businesses and legal cases

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

    proper nouns and brand names.

    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
     disambiguazione
    -0.44
    se
    -0.35
    ed
    -0.32
    em
    -0.31
    est
    -0.30
    y
    -0.29
    <h2>
    -0.28
    armée
    -0.28
    les
    -0.27
     alltså
    -0.27
    POSITIVE LOGITS
    SequentialGroup
    0.66
     فريبيس
    0.65
    RTEX
    0.65
     كومونز
    0.61
     <<<<<<<<<<<<<<
    0.53
     Excelsior
    0.53
    AndEndTag
    0.53
    ᅠ
    0.53
    IBOutlet
    0.52
    featureID
    0.52
    Activations Density 0.551%

    No Known Activations