© 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. 20-GEMMASCOPE-RES-16K
    11. 6905
    Prev
    Next
    INDEX
    Explanations

    references to support systems and community networks

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

    Forms of "support" or encouragement

    np_acts-logits-general · gemini-2.0-flash

    support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.80
    ंदीखरीदारी
    -0.65
     sqlalchemy
    -0.64
     PLWABN
    -0.64
    SuppressLint
    -0.61
     estekak
    -0.59
    TargetException
    -0.57
     onCreateView
    -0.57
    HandlerContext
    -0.55
     initComponents
    -0.54
    POSITIVE LOGITS
     support
    2.94
    support
    2.60
     Support
    2.57
    Support
    2.52
     SUPPORT
    2.40
    SUPPORT
    2.30
     supportive
    2.26
     supporting
    2.24
     supports
    2.17
     soutien
    2.07
    Activations Density 0.402%

    No Known Activations