© 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
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9417
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to statistical models or equations

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

    mathematical superscripts with negative exponents, particularly -1 notation in equations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    beitrag
    -0.47
    SceneManagement
    -0.44
     برانيه
    -0.43
     volna
    -0.43
    zőkönyv
    -0.42
     تضيفلها
    -0.41
    takings
    -0.40
     jegy
    -0.40
    扯
    -0.39
     auroit
    -0.39
    POSITIVE LOGITS
    ^{-
    1.42
    }^{-
    1.38
     ^{-
    1.20
    )^{-
    1.19
    ]^{-
    1.12
     }^{-
    1.01
    ^{-\
    0.92
    ^(-
    0.79
    $^{-
    0.72
    }^{-\
    0.70
    Activations Density 0.499%

    No Known Activations