© 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. 24-GEMMASCOPE-RES-16K
    6. 15866
    Prev
    Next
    INDEX
    Explanations

    instructions or suggestions regarding technical setups and configurations

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

    "Enable" or "disable" appearing in text

    np_acts-logits-general · gemini-2.0-flash

    enabled or disabled

    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
    itemBuilder
    -0.55
    MessageTagHelper
    -0.55
    AnchorTagHelper
    -0.53
     MenuView
    -0.52
    CopyWith
    -0.52
     imprimée
    -0.52
     autorytatywna
    -0.52
    MigrationBuilder
    -0.48
    minipage
    -0.48
     NSCoder
    -0.48
    POSITIVE LOGITS
     enabled
    1.79
     enable
    1.72
     disable
    1.71
     Enable
    1.66
     disabled
    1.64
     Disable
    1.56
    Enable
    1.52
    enable
    1.52
     disabling
    1.50
     Enabled
    1.50
    Activations Density 0.564%

    No Known Activations