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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8606
    Prev
    Next
    INDEX
    Explanations

    mathematical notations or symbols that indicate mathematical expressions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BrowserModule
    -0.50
     daarbij
    -0.48
     parseFrom
    -0.48
    toArray
    -0.47
     prostu
    -0.47
     Harms
    -0.46
    /-
    -0.46
    ujte
    -0.46
     IActionResult
    -0.45
     Concerns
    -0.44
    POSITIVE LOGITS
    ^{-
    1.05
    }^{-
    0.96
    }^{+
    0.74
    ^{-}\
    0.69
    ^{+
    0.69
     }^{-
    0.69
    }^{-}\
    0.67
     ^{-
    0.66
    ]^{-
    0.66
    ^{-}
    0.64
    Activations Density 0.116%

    No Known Activations