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. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7175
    Prev
    Next
    INDEX
    Explanations

    contexts involving social dynamics and interpersonal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OMITBAD
    -0.56
     unknownFields
    -0.46
    TestingModule
    -0.45
     transfieras
    -0.43
    uldron
    -0.39
    ágenes
    -0.39
    
    -0.38
    のですか
    -0.37
    Portail
    -0.37
    şört
    -0.35
    POSITIVE LOGITS
     also
    0.55
     też
    0.55
     también
    0.49
     også
    0.48
     επίσης
    0.47
     também
    0.45
     inoltre
    0.45
     myös
    0.44
     également
    0.43
    anche
    0.43
    Activations Density 0.985%

    No Known Activations