Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 558
    Prev
    Next
    INDEX
    Explanations

    references to programming languages and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doPost
    -0.42
    )"),
    -0.42
    ThroughAttribute
    -0.39
     big
    -0.39
    ']")
    -0.39
    })),
    -0.38
    '}),
    -0.38
    }))
    -0.38
    outState
    -0.38
     top
    -0.37
    POSITIVE LOGITS
     Language
    1.16
    Language
    1.15
     language
    1.15
    language
    1.03
    anguage
    1.02
     LANGUAGE
    1.02
    LANGUAGE
    0.97
     Languages
    0.95
     languages
    0.93
    Languages
    0.92
    Activations Density 0.191%

    No Known Activations