© 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. 11-GEMMASCOPE-RES-16K
    6. 6418
    Prev
    Next
    INDEX
    Explanations

    sections marked with the beginning of a document or important points in a text structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.90
    InputBorder
    -0.90
    XmlAccessType
    -0.83
    RuleContext
    -0.82
     jScrollPane
    -0.81
    MessageState
    -0.80
    ReusableCell
    -0.80
    bkz
    -0.79
     jLabel
    -0.77
    Демографія
    -0.75
    POSITIVE LOGITS
    ame
    0.50
    <bos>
    0.48
    a
    0.46
    ü
    0.45
    in
    0.45
    Content
    0.45
    ”
    0.44
    b
    0.44
    le
    0.44
    hy
    0.44
    Activations Density 0.120%

    No Known Activations