© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 8361
    Prev
    Next
    INDEX
    Explanations

    references to comparisons or analogies

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

    like "mini" and "little"

    np_acts-logits-general · gemini-2.0-flash

    miniature or little things being compared

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.89
    rrggbb
    -0.63
    [--
    -0.58
     kvinna
    -0.56
    ($__
    -0.55
     acrylique
    -0.54
     antaranya
    -0.53
     AspNetCore
    -0.53
     kaynağından
    -0.52
    Referencie
    -0.52
    POSITIVE LOGITS
     mini
    1.22
     miniature
    1.05
    mini
    0.94
     equivalent
    0.83
    miniature
    0.82
     Mini
    0.81
    Mini
    0.79
    版的
    0.74
     little
    0.69
     Little
    0.69
    Activations Density 0.340%

    No Known Activations