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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 5758
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate welcoming or introductory statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intit
    -0.57
     supposed
    -0.56
     تضيفلها
    -0.53
    出版年
    -0.51
    ोंने
    -0.49
     StringVar
    -0.48
    usda
    -0.48
    taobao
    -0.47
     connues
    -0.46
     Hima
    -0.45
    POSITIVE LOGITS
    Portail
    0.76
     kasarigan
    0.74
     Италијани
    0.70
     our
    0.68
    bulo
    0.67
    (!__
    0.66
     Chwiliwch
    0.65
    migrationBuilder
    0.63
    GrantedAuthority
    0.62
    tvguidetime
    0.62
    Activations Density 0.199%

    No Known Activations