© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105596
    Prev
    Next
    INDEX
    Explanations

    patterns and markers in numerical or coded data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    новништво
    -0.68
    ]")]
    -0.65
    tagHelperRunner
    -0.65
    webElementXpaths
    -0.63
    __':
    -0.61
    ghijkl
    -0.60
    TypedDataSet
    -0.59
    "):
    -0.59
     ExecuteAsync
    -0.58
    })));
    -0.58
    POSITIVE LOGITS
    ItemBackground
    0.45
     AssemblyCompany
    0.41
     المعيارى
    0.37
     étranger
    0.34
     heridas
    0.34
     abstrait
    0.32
     antigüedad
    0.32
     cortos
    0.32
    icznie
    0.31
     misalnya
    0.31
    Activations Density 0.314%

    No Known Activations