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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109879
    Prev
    Next
    INDEX
    Explanations

    instances of the word "derive" and its variations, indicating a focus on derivation processes or formulae in mathematical or scientific contexts

    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
     derived
    -1.05
    derived
    -0.86
     Derived
    -0.86
     deriving
    -0.86
     derive
    -0.82
    Derived
    -0.80
     derivation
    -0.76
     derives
    -0.76
     derivados
    -0.65
    derive
    -0.63
    POSITIVE LOGITS
    ftagPool
    0.51
    GEBURTS
    0.50
    ArgsConstructor
    0.49
    دانشنامهٔ
    0.49
     /\.(
    0.48
    \{\\
    0.47
    HasColumnName
    0.47
    endforeach
    0.46
    ########.
    0.46
    enumi
    0.44
    Activations Density 0.015%

    No Known Activations