© 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. 22-GEMMASCOPE-RES-16K
    6. 8902
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their attributes in code

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

    Followed by "info"

    np_acts-logits-general · gemini-2.0-flash

    information or info

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taza
    -0.45
    hagy
    -0.44
    ாய
    -0.44
    udder
    -0.42
     OMIT
    -0.41
    ́ng
    -0.41
     DialogResult
    -0.41
    例句
    -0.41
    TestTools
    -0.41
     vå
    -0.40
    POSITIVE LOGITS
     info
    3.24
    info
    3.16
     Info
    2.97
    Info
    2.93
     information
    2.54
     INFO
    2.43
    INFO
    2.38
     Information
    2.29
    information
    2.20
     INFORMATION
    2.17
    Activations Density 0.112%

    No Known Activations