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-2-2B
    4. MLP Out - 65k
    5. 0-GEMMASCOPE-MLP-65K
    6. 61067
    Prev
    Next
    INDEX
    Explanations

    terms related to culpability or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    padek
    -0.75
    ignty
    -0.74
    withIdentifier
    -0.70
    bility
    -0.69
    ficulty
    -0.68
    avelength
    -0.68
    terness
    -0.68
    authorised
    -0.67
     suena
    -0.67
    curacy
    -0.66
    POSITIVE LOGITS
    ’.
    0.79
    ("]");
    0.78
     ModelExpression
    0.76
     المعيارى
    0.75
    ]</
    0.74
    ”.
    0.71
    })`
    0.70
     }</
    0.69
    :],
    0.69
    ].
    0.68
    Activations Density 0.021%

    No Known Activations