© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10915
    Prev
    Next
    INDEX
    Explanations

    references to political ethics and legislative actions

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

    New York laws or statutes

    np_acts-logits-general · gemini-2.0-flash

    law and legislation

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     estekak
    -0.70
     שוליים
    -0.57
    enterOuterAlt
    -0.55
     Administrativna
    -0.54
    angliski
    -0.53
     tartalomajánló
    -0.51
    脚注の使い方
    -0.50
     дописавши
    -0.50
     Persönlichkeit
    -0.50
    (;;)
    -0.49
    POSITIVE LOGITS
    ngrx
    0.41
    AsUp
    0.40
     Bail
    0.38
     supra
    0.37
     lob
    0.37
     Cuomo
    0.36
    Bail
    0.35
    󠁣
    0.34
    phosa
    0.34
    ➋
    0.33
    Activations Density 0.256%

    No Known Activations