© 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. 5-GEMMASCOPE-RES-16K
    11. 6617
    Prev
    Next
    INDEX
    Explanations

    phrases describing relative comparisons or levels of quantity and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    on
    -0.71
    !
    -0.67
    my
    -0.65
    an
    -0.65
     opérateur
    -0.63
    (
    -0.60
    *
    -0.59
    le
    -0.58
    in
    -0.58
    DA
    -0.58
    POSITIVE LOGITS
    relatively
    1.86
     relatively
    1.83
     Relatively
    1.79
     fairly
    1.45
     relativamente
    1.42
     comparatively
    1.39
     Fairly
    1.31
     relativement
    1.31
     relativ
    1.22
     Мексичка
    1.18
    Activations Density 0.068%

    No Known Activations