© 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. 4542
    Prev
    Next
    INDEX
    Explanations

    the word "always" and its contexts, indicating a focus on consistency and continuity in experiences or statements

    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
     often
    -0.96
     måske
    -0.79
     misschien
    -0.74
     sometimes
    -0.70
     also
    -0.67
     spesso
    -0.67
     często
    -0.67
     často
    -0.66
     artık
    -0.66
    often
    -0.66
    POSITIVE LOGITS
     defaultstate
    0.67
     wondered
    0.64
     Италијани
    0.59
    cky
    0.59
     bridesmaid
    0.58
     been
    0.57
     digo
    0.57
     dreamed
    0.56
     excepting
    0.56
     محفوظة
    0.54
    Activations Density 0.164%

    No Known Activations