© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 45741
    Prev
    Next
    INDEX
    Explanations

    references to people or entities related to sports and academic publications

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

    PhysRevLett citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gossip
    -0.38
    useEffect
    -0.35
     deferred
    -0.34
    ●
    -0.33
     static
    -0.32
     Try
    -0.32
     poved
    -0.32
     Static
    -0.32
     tł
    -0.32
     Hogg
    -0.31
    POSITIVE LOGITS
    Personendaten
    0.90
    +#+#
    0.88
    ngdoc
    0.83
     disambiguazione
    0.82
     Normdatei
    0.77
    PhysRevLett
    0.75
    textwidth
    0.71
    IconModule
    0.69
     للمعارف
    0.67
    SPJ
    0.67
    Activations Density 0.007%

    No Known Activations