© 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. 9704
    Prev
    Next
    INDEX
    Explanations

    verbs indicating past actions or states

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

    Follows the token "was"

    np_acts-logits-general · gemini-2.0-flash

    describing past events

    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
     againſt
    -0.67
     habet
    -0.61
     ejus
    -0.60
     Chriftian
    -0.58
    見えて
    -0.58
     Jefus
    -0.57
     fince
    -0.56
    見えます
    -0.55
     eorum
    -0.54
     omnia
    -0.54
    POSITIVE LOGITS
     also
    1.06
     actually
    0.88
     was
    0.88
     originally
    0.87
     never
    0.87
     indeed
    0.85
     certainly
    0.85
     not
    0.84
     always
    0.83
     Was
    0.82
    Activations Density 0.456%

    No Known Activations