© 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. 335
    Prev
    Next
    INDEX
    Explanations

    tags associated with various elements or items in a structured format

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

    "Tag" followed by archives or a colon

    np_acts-logits-general · gemini-2.0-flash

    tag followed by related content

    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
     Reverso
    -0.62
    Portail
    -0.49
    中には
    -0.48
    MessageId
    -0.47
    <strong>
    -0.47
     điển
    -0.46
    atoires
    -0.44
    θεια
    -0.43
    zation
    -0.43
    CrossRef
    -0.43
    POSITIVE LOGITS
     tags
    1.52
     tag
    1.41
     Tag
    1.38
     Tags
    1.33
     TAG
    1.28
    tags
    1.25
     TAGS
    1.21
     tagging
    1.19
    Tag
    1.17
     标签
    1.10
    Activations Density 0.060%

    No Known Activations