© 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. 20-GEMMASCOPE-RES-131K
    6. 73666
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to coding languages and data structures

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

    mathematical and code expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.69
     surla
    -0.61
    Portail
    -0.54
    Попис
    -0.53
    styleType
    -0.53
     وتسجيلات
    -0.50
     utafitiHapana
    -0.50
     referrerpolicy
    -0.50
    IContainer
    -0.50
     ब्रेकडाउन
    -0.49
    POSITIVE LOGITS
    )))),
    0.42
     ja
    0.33
    []>(
    0.33
    ')")
    0.30
    )-
    0.29
    }))
    
    0.29
    est
    0.28
    乏
    0.28
    )
    
    
    0.28
    global
    0.27
    Activations Density 0.349%

    No Known Activations