© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 808
    Prev
    Next
    INDEX
    Explanations

    JavaScript object syntax and structures

    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
    bewerken
    -0.65
    KURZBESCHREIBUNG
    -0.60
     facili
    -0.58
    ียง
    -0.57
    autorest
    -0.56
     ostavi
    -0.54
     transfieras
    -0.54
     Ostat
    -0.53
     lick
    -0.53
    Vidite
    -0.53
    POSITIVE LOGITS
     propOrder
    0.63
    Toponymie
    0.60
    rungsseite
    0.58
     pungkasnya
    0.55
    SourceChecksum
    0.54
     sentimentos
    0.53
    bindParam
    0.52
     pageable
    0.52
     ucapnya
    0.52
     &___
    0.51
    Activations Density 0.093%

    No Known Activations