© 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. 3-GEMMASCOPE-RES-16K
    11. 8162
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'out'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelves
    -0.84
    ftagPool
    -0.80
    SPATH
    -0.79
    IntoConstraints
    -0.79
    ſelf
    -0.76
     ſtate
    -0.72
     uſed
    -0.72
     ſen
    -0.72
     समीक्षाएं
    -0.72
     Efq
    -0.72
    POSITIVE LOGITS
    ьаж
    0.62
     turnout
    0.61
    bewerken
    0.56
    LookAnd
    0.50
    DrawerToggle
    0.50
    pires
    0.50
    湃
    0.49
    interopRequire
    0.49
     Outcomes
    0.49
    execSQL
    0.48
    Activations Density 0.253%

    No Known Activations