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. 109434
    Prev
    Next
    INDEX
    Explanations

    empty or unspecified input fields in forms

    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
    ScopeManager
    -0.62
    Personensuche
    -0.61
    AddTagHelper
    -0.61
    tagHelperRunner
    -0.61
     ब्रेकडाउन
    -0.60
    featureID
    -0.60
     للاسماء
    -0.59
    Tikang
    -0.58
    ConstraintMaker
    -0.57
    帖最后由
    -0.55
    POSITIVE LOGITS
    抱
    0.38
    明
    0.37
    arschu
    0.37
     Seb
    0.37
    Становништво
    0.36
    Życiorys
    0.36
     oku
    0.36
     desac
    0.35
     sketches
    0.35
    강
    0.35
    Activations Density 0.004%

    No Known Activations