© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8797
    Prev
    Next
    INDEX
    Explanations

    instances of claims or reports within formal or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gynhyrchwyd
    -0.58
    AnimationsModule
    -0.58
     оригіналу
    -0.56
    DeleteBehavior
    -0.55
    tagHelperRunner
    -0.53
    帖最后由
    -0.52
     المعيارى
    -0.51
    脚注の使い方
    -0.51
     //$
    -0.51
    󠁢
    -0.50
    POSITIVE LOGITS
    findpost
    0.75
     GBIF
    0.66
     resourceCulture
    0.65
     ")");
    0.63
     helico
    0.62
     EnglishChoose
    0.62
    Datuak
    0.60
     auffi
    0.60
     Chaco
    0.60
    adpleegd
    0.59
    Activations Density 0.339%

    No Known Activations