© 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. 18-GEMMASCOPE-RES-16K
    11. 6626
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative adjectives

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

    following "more", "most", or "as"

    np_acts-logits-general · gemini-2.0-flash

    degree of adjectives

    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
    very
    -0.71
    Very
    -0.69
     dépos
    -0.67
     migliore
    -0.67
     tantôt
    -0.64
     semakin
    -0.64
     pério
    -0.63
     migliori
    -0.62
     Very
    -0.61
     tantum
    -0.60
    POSITIVE LOGITS
    :✨
    0.74
     prevalent
    0.62
     prominent
    0.62
     pronounced
    0.62
     effective
    0.61
     reliant
    0.61
     likely
    0.61
     well
    0.60
     efficient
    0.58
     closely
    0.58
    Activations Density 0.365%

    No Known Activations