© 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. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 109102
    Prev
    Next
    INDEX
    Explanations

    details related to human hair characteristics and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wußt
    -0.42
    tagext
    -0.41
    :✨
    -0.40
    Constantes
    -0.38
    舺
    -0.38
    IUrlHelper
    -0.38
     occaf
    -0.37
     occafion
    -0.36
    calientes
    -0.36
    Ensure
    -0.35
    POSITIVE LOGITS
    StackNavigator
    0.50
    ArgsConstructor
    0.46
    Werdegang
    0.45
    fillType
    0.44
    dataclass
    0.40
     defaultstate
    0.40
    Xna
    0.39
    CppMethod
    0.39
    onema
    0.38
    RetentionPolicy
    0.38
    Activations Density 0.025%

    No Known Activations