© 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. 2562
    Prev
    Next
    INDEX
    Explanations

    references to specific types of data structures or functions in programming contexts

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

    Hexadecimal strings

    np_acts-logits-general · gemini-2.0-flash

    UUIDs with 'cf' or 'bdf'

    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
    enumi
    -0.62
    orius
    -0.56
    toria
    -0.56
    eer
    -0.55
     resourceCulture
    -0.55
     BorderSide
    -0.55
     useAppContext
    -0.55
    Demografie
    -0.54
     مرئيه
    -0.52
    tors
    -0.51
    POSITIVE LOGITS
     '\\;'
    0.59
    ed
    0.56
    rank
    0.55
    lash
    0.51
    actory
    0.51
    IsContent
    0.51
    amily
    0.51
    usion
    0.50
    resh
    0.49
    ocus
    0.48
    Activations Density 0.320%

    No Known Activations