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. 60903
    Prev
    Next
    INDEX
    Explanations

    the end of sections or paragraphs in text

    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
    end
    -1.63
     end
    -1.39
    End
    -1.18
     End
    -1.14
     END
    -0.92
    WebVitals
    -0.85
     poveznice
    -0.83
    setcounter
    -0.82
     ends
    -0.81
    </table>
    -0.79
    POSITIVE LOGITS
     Theſe
    0.57
     Efq
    0.57
    nés
    0.56
     Monfieur
    0.56
     Kühlschrank
    0.55
    baarheid
    0.54
     Leyden
    0.54
     Dand
    0.54
    ñores
    0.54
     doubtnut
    0.53
    Activations Density 0.016%

    No Known Activations