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. 12-GEMMASCOPE-RES-16K
    6. 11826
    Prev
    Next
    INDEX
    Explanations

    references to physical locations or structures in relation to an environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.60
     SwiftUI
    -0.59
    PullParser
    -0.58
     sails
    -0.56
    AddHtmlAttribute
    -0.56
    stateParams
    -0.56
     Tait
    -0.55
     ModelAndView
    -0.54
     Erzb
    -0.54
    Smarty
    -0.53
    POSITIVE LOGITS
     bottom
    1.08
     Bottom
    1.01
     BOTTOM
    0.99
     Beneath
    0.96
     beneath
    0.95
    bottom
    0.94
    Beneath
    0.94
    Bottom
    0.93
     below
    0.91
     BELOW
    0.90
    Activations Density 0.546%

    No Known Activations