© 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. 4-GEMMASCOPE-RES-16K
    11. 11325
    Prev
    Next
    INDEX
    Explanations

    references to statistical models and data analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    -0.95
     '
    -0.80
    <eos>
    -0.76
     “
    -0.73
    "
    -0.71
     S
    -0.69
     N
    -0.69
    -
    -0.68
     -
    -0.67
     L
    -0.65
    POSITIVE LOGITS
     itſelf
    1.41
     myſelf
    1.40
     (\<
    1.33
    ſelves
    1.28
     photolibrary
    1.28
     leſs
    1.27
     (§
    1.24
     Theſe
    1.24
     ſind
    1.22
     raiſ
    1.20
    Activations Density 0.828%

    No Known Activations