© 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. 7930
    Prev
    Next
    INDEX
    Explanations

    structured data points or identifiers related to user interactions

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

    Code or math delimiters

    np_acts-logits-general · gemini-2.0-flash

    Leb and formulas

    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
     PLOS
    -0.65
     Matheson
    -0.64
     Allison
    -0.63
     Wint
    -0.63
     Dickens
    -0.60
     Milner
    -0.59
    Allison
    -0.59
     eqn
    -0.58
     Sexton
    -0.58
     Irving
    -0.58
    POSITIVE LOGITS
     Reinh
    0.73
     Cognac
    0.73
     Cough
    0.70
     Schofield
    0.70
    Flynn
    0.66
     Elijah
    0.66
     Steiner
    0.65
     Flynn
    0.65
     Goh
    0.64
    annah
    0.64
    Activations Density 1.347%

    No Known Activations