© 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. 25-GEMMASCOPE-RES-16K
    11. 8241
    Prev
    Next
    INDEX
    Explanations

    instances of the word "already" and related terms indicating prior actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     still
    -1.33
    still
    -1.31
     todavía
    -1.13
     ancora
    -1.10
     aún
    -1.08
     هنوز
    -1.06
    Still
    -1.05
     also
    -1.05
     Still
    -1.03
     ainda
    -1.02
    POSITIVE LOGITS
     begun
    0.70
     established
    0.67
     resourceCulture
    0.64
    IsMutable
    0.64
     underway
    0.62
     halfway
    0.61
     existente
    0.61
     knew
    0.61
    Kjelder
    0.60
     existant
    0.60
    Activations Density 0.108%

    No Known Activations