© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 16064
    Prev
    Next
    INDEX
    Explanations

    references to technical or computational concepts

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

    followed by a measurement unit or type

    np_acts-logits-general · gemini-2.0-flash

    size and position metadata

    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
    Попис
    -0.65
    lapsingToolbar
    -0.59
    Museum
    -0.57
    Commercial
    -0.56
    Casino
    -0.56
    Commun
    -0.55
    Surgical
    -0.55
    Collaborative
    -0.53
    Parser
    -0.53
    Interactive
    -0.53
    POSITIVE LOGITS
     Size
    1.15
     Value
    1.11
     Name
    1.08
     Level
    1.05
     Age
    1.03
     Amount
    1.02
     Position
    1.02
     Length
    1.00
     Rate
    0.98
     Height
    0.96
    Activations Density 0.732%

    No Known Activations