© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12300
    Prev
    Next
    INDEX
    Explanations

    phrases that involve questions or inquiries

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

    Words/phrases followed by an asterisk

    np_acts-logits-general · gemini-2.0-flash

    `*` delimiters around words

    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
      
    -1.41
    </b>
    -1.20
    ViewFeatures
    -1.19
    SourceChecksum
    -1.10
    </strong>
    -1.04
    tagHelperRunner
    -0.98
     ​
    -0.97
    setVerticalGroup
    -0.95
    
    -0.90
    !—
    -0.90
    POSITIVE LOGITS
     *
    0.58
     *,
    0.57
    』(
    0.55
    *-
    0.52
    **/
    0.52
    *.
    0.52
    *
    0.52
    ]*
    0.49
    *$
    0.49
    *,
    0.48
    Activations Density 0.015%

    No Known Activations