© 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. 108060
    Prev
    Next
    INDEX
    Explanations

    actions related to managing or dealing with various tasks and situations

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

    handling tasks and items

    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
    MediaStore
    -0.43
    )))))
    -0.41
    ']))
    -0.37
     poster
    -0.37
    诰
    -0.37
    }})
    -0.35
    }}}
    -0.34
     Socialista
    -0.34
     neon
    -0.33
     commune
    -0.33
    POSITIVE LOGITS
    handled
    1.11
     Handling
    1.02
     handled
    1.00
    handling
    0.98
     Handle
    0.97
    Handling
    0.97
     handling
    0.95
    handle
    0.94
    Handled
    0.93
    HANDLING
    0.88
    Activations Density 0.012%

    No Known Activations