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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2235
    Prev
    Next
    INDEX
    Explanations

    structured mathematical expressions or notation

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

    Mathematical or set notation

    np_acts-logits-general · gemini-2.0-flash

    indices and delimiters

    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
    "
    -1.24
    (
    -1.15
    :
    -1.02
    '
    -0.93
    ?
    -0.93
    -0.90
    \
    -0.88
    [
    -0.84
    .
    -0.82
    !
    -0.81
    POSITIVE LOGITS
     ...,
    1.12
     *,
    0.98
     "",
    0.90
    _,
    0.89
    __,
    0.87
    *,
    0.86
     _,
    0.85
     '',
    0.84
     ?,
    0.84
     {},
    0.84
    Activations Density 0.791%

    No Known Activations