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. 18-GEMMASCOPE-RES-16K
    6. 14342
    Prev
    Next
    INDEX
    Explanations

    mentions of specific chemical compounds or substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, math, or chemical nomenclature

    np_acts-logits-general · gemini-2.0-flash

    code and academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    遥
    -0.53
    VersionUID
    -0.50
    matsu
    -0.48
    enciais
    -0.46
     Libby
    -0.46
     setObject
    -0.46
    Gone
    -0.46
     mess
    -0.44
    はじめに
    -0.44
    iber
    -0.43
    POSITIVE LOGITS
     Meksiku
    0.82
     Италијани
    0.73
    IUrlHelper
    0.66
     démocratique
    0.65
     disponibilités
    0.61
     propOrder
    0.61
     ripet
    0.61
    ")));
    
    0.60
     bide
    0.58
    '])->
    0.57
    Activations Density 0.252%

    No Known Activations