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. 22-GEMMASCOPE-RES-16K
    6. 6031
    Prev
    Next
    INDEX
    Explanations

    quantitative data and numerical representations in text

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

    Mathematical notation delimiters

    np_acts-logits-general · gemini-2.0-flash

    mathematical theorems and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    databind
    -0.83
     ’
    -0.80
     “
    -0.76
     ‘‘
    -0.75
     ”
    -0.72
    ,’’
    -0.70
     ‘
    -0.70
     …”
    -0.70
    …”
    -0.70
     ‘’
    -0.70
    POSITIVE LOGITS
    \
    1.77
    \[
    1.16
    \&
    0.93
    \%)
    0.89
    \\
    0.89
    \#
    0.86
     \&
    0.81
     $=$
    0.81
    $\
    0.81
    $>$
    0.81
    Activations Density 0.133%

    No Known Activations