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-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109637
    Prev
    Next
    INDEX
    Explanations

    questions and prompts seeking advice or insights about personal experiences

    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
    WriteTagHelper
    -0.74
     CURIAM
    -0.73
    CloseOperation
    -0.71
    ChildScrollView
    -0.69
    OGND
    -0.66
    EDEFAULT
    -0.66
    RefNanny
    -0.65
    LookAnd
    -0.63
    StructEnd
    -0.61
    InjectAttribute
    -0.60
    POSITIVE LOGITS
    ')}}">
    0.46
    angor
    0.36
     mag
    0.35
    ])));
    0.33
    ('/');
    0.33
    ?=
    0.33
    )}-\
    0.33
    ']))
    
    0.32
    )"),
    0.32
     hom
    0.31
    Activations Density 0.206%

    No Known Activations