© 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. 6-GEMMASCOPE-RES-16K
    11. 3824
    Prev
    Next
    INDEX
    Explanations

    terms related to data ownership and privacy policies

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

    phrases related to data privacy, information ownership, and licensing agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     halla
    -0.56
    TacToe
    -0.55
    flé
    -0.54
    mlı
    -0.50
    zade
    -0.49
    itan
    -0.48
    รม
    -0.46
    tilha
    -0.46
    lux
    -0.45
    chera
    -0.45
    POSITIVE LOGITS
     ModelExpression
    1.14
    LookAnd
    1.13
    GEBURTSDATUM
    1.09
    webElementXpaths
    1.09
    ftagPool
    1.03
    EDEFAULT
    1.02
    تقاوى
    1.02
     виправивши
    1.01
     beginnetje
    1.00
    ConstraintMaker
    0.99
    Activations Density 0.698%

    No Known Activations