© 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. 6775
    Prev
    Next
    INDEX
    Explanations

    phrases indicating insufficient size or capacity in various contexts

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

    [Adjective] enough

    np_acts-logits-general · gemini-2.0-flash

    adjectives of measure followed by enough

    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
    etCode
    -0.57
    geblich
    -0.55
    таратура
    -0.50
    plz
    -0.49
    esgue
    -0.48
    kiwa
    -0.46
    ūsų
    -0.46
    maar
    -0.45
    Архівовано
    -0.44
     initialState
    -0.44
    POSITIVE LOGITS
     enough
    3.71
    enough
    3.35
     Enough
    3.22
     ENOUGH
    2.94
    Enough
    2.93
     sufficient
    2.74
     sufficiently
    2.53
     genug
    2.48
     Sufficient
    2.46
    sufficient
    2.38
    Activations Density 0.704%

    No Known Activations