© 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. 13969
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and URLs related to a blog or website

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

    Dejal.org news and emails

    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
     Reſ
    -0.81
    ſelf
    -0.80
     ſche
    -0.77
     ſch
    -0.77
     ſta
    -0.75
     faſt
    -0.75
     Conſ
    -0.74
     fubject
    -0.73
     Verſ
    -0.73
     Anſ
    -0.73
    POSITIVE LOGITS
    
    0.40
    tagHelperRunner
    0.39
    tgz
    0.35
    "])
    0.34
     @"/
    0.34
    SneakyThrows
    0.33
    urlencoded
    0.32
    }")
    0.32
    ExtendWith
    0.32
    >')
    0.30
    Activations Density 0.206%

    No Known Activations