© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1842
    Prev
    Next
    INDEX
    Explanations

    commands related to managing application configurations or resources

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

    Tokens preceding words like "credential", "encryption", or "replication"

    np_acts-logits-general · gemini-2.0-flash

    acr credential commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Div
    -0.36
    Re
    -0.35
    Deg
    -0.35
    Bin
    -0.35
    Or
    -0.35
    Cho
    -0.35
    Qu
    -0.35
    Per
    -0.34
    End
    -0.34
    Cos
    -0.34
    POSITIVE LOGITS
    tagHelperRunner
    0.38
    full
    0.37
    user
    0.37
    index
    0.36
    self
    0.36
    update
    0.36
    list
    0.36
    info
    0.35
    default
    0.35
    input
    0.35
    Activations Density 11.052%

    No Known Activations