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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10663
    Prev
    Next
    INDEX
    Explanations

    actions and verbs related to manual tasks or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insuffisamment
    -0.62
    +:+
    -0.59
    DispatchToProps
    -0.56
     kasarigan
    -0.53
     Offisielt
    -0.53
    Sebagai
    -0.50
    archiviato
    -0.49
    ußer
    -0.47
     typelib
    -0.47
     snippetHide
    -0.46
    POSITIVE LOGITS
     up
    0.92
     them
    0.84
     down
    0.83
     out
    0.80
     ulang
    0.73
     away
    0.72
     it
    0.69
     back
    0.65
     him
    0.64
     into
    0.63
    Activations Density 0.438%

    No Known Activations