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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 12844
    Prev
    Next
    INDEX
    Explanations

    instances of array structures in mathematical or programming contexts

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

    LaTeX math environments

    np_acts-logits-general · gemini-2.0-flash

    latex array environments

    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
    TargetException
    -0.70
    saraba
    -0.64
    Према
    -0.55
    windowFixed
    -0.51
    awaiter
    -0.51
    namics
    -0.51
    ngdoc
    -0.50
     Hügel
    -0.50
     setuptools
    -0.49
    имость
    -0.49
    POSITIVE LOGITS
    enumi
    0.63
    enumii
    0.53
    tvguidetime
    0.53
     StringTokenizer
    0.52
    Referanser
    0.48
    RenderAtEndOf
    0.48
     дописавши
    0.47
    ReusableCell
    0.46
    orth
    0.46
    voorbeeld
    0.46
    Activations Density 0.104%

    No Known Activations