© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11908
    Prev
    Next
    INDEX
    Explanations

    patterns of list syntax and structure

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

    Opening files using argv[0]

    np_acts-logits-general · gemini-2.0-flash

    code syntax and file operations

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     QtGui
    -0.52
    ("")]
    -0.49
    ')))
    -0.48
    )))),
    -0.47
    pyplot
    -0.45
     }]
    -0.44
    ]].
    -0.43
     laud
    -0.43
    }],
    -0.42
    isma
    -0.42
    POSITIVE LOGITS
     almofada
    0.62
     prefeitura
    0.60
     vectorielle
    0.59
    principalColumn
    0.59
     desmotivaciones
    0.58
     pegatinas
    0.57
     traseira
    0.56
     gynhyrchwyd
    0.55
     CURIAM
    0.55
     felicidade
    0.54
    Activations Density 0.122%

    No Known Activations