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. 8-GEMMASCOPE-RES-16K
    6. 8602
    Prev
    Next
    INDEX
    Explanations

    terms related to veganism and plant-based concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.97
     Roskov
    -0.96
    extAlignment
    -0.95
    WebVitals
    -0.93
    elemField
    -0.92
    IsContent
    -0.92
    Geplaatst
    -0.90
     MainAxisSize
    -0.90
    migrationBuilder
    -0.88
    sizeCache
    -0.86
    POSITIVE LOGITS
     ​​
    0.53
    <em>
    0.45
    ключения
    0.44
     bin
    0.42
     rzecz
    0.40
     ($)
    0.40
    <strong>
    0.40
     themed
    0.39
     nip
    0.39
    ICOS
    0.39
    Activations Density 1.043%

    No Known Activations