© 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. 3981
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential actions or considerations

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

    "Might" or "may" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    might be followed by adjective/participle

    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
     evidently
    -1.01
     presumably
    -0.98
     apparently
    -0.93
    presumably
    -0.92
     obviously
    -0.90
     basically
    -0.86
     usually
    -0.86
     Presumably
    -0.84
    apparently
    -0.84
     Evidently
    -0.83
    POSITIVE LOGITS
     jopa
    1.00
    anskje
    0.99
     algún
    0.93
     depending
    0.93
     someday
    0.89
    depending
    0.83
     some
    0.80
     sogar
    0.78
     might
    0.77
     zelfs
    0.75
    Activations Density 0.588%

    No Known Activations