Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4356
    Prev
    Next
    INDEX
    Explanations

    code structure and definitions in programming languages

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

    Code-related terms and symbols

    np_acts-logits-general · gemini-2.0-flash

    associations. ) & (\ the -

    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
    ViewStyle
    -0.54
    COUVER
    -0.53
    barrow
    -0.50
    culous
    -0.50
    thood
    -0.46
    ifflin
    -0.46
    leicht
    -0.46
     neur
    -0.44
     naive
    -0.44
    FLO
    -0.44
    POSITIVE LOGITS
    SupportActionBar
    0.69
     propOrder
    0.59
    SerializeField
    0.59
    tagext
    0.59
     []:
    0.55
     NUKAT
    0.55
    omitempty
    0.54
     चीज़ों
    0.54
    حياته
    0.52
    DockStyle
    0.52
    Activations Density 0.036%

    No Known Activations