© 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. 6702
    Prev
    Next
    INDEX
    Explanations

    specific indicators of importance or prominence in a text, such as key terms, identifiers, or distinguishing elements that reflect significance in context

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

    drive display

    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
    ässe
    -0.32
    ]=>
    -0.32
    igshid
    -0.32
    laway
    -0.31
    spli
    -0.31
    getSystemService
    -0.31
    chule
    -0.31
     torpedo
    -0.30
    Tail
    -0.29
     Cryst
    -0.29
    POSITIVE LOGITS
    AccessorTable
    0.64
     ujednoznacz
    0.56
    ReusableCell
    0.52
    ########.
    0.51
     esternos
    0.50
    
    0.50
    XtraReports
    0.50
    الحياه
    0.49
    EDEFAULT
    0.49
    ftc
    0.48
    Activations Density 0.076%

    No Known Activations