© 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. 22-GEMMASCOPE-RES-16K
    11. 16286
    Prev
    Next
    INDEX
    Explanations

    words related to freshness

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

    "fresh"

    np_acts-logits-general · gemini-2.0-flash

    fresh context descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DispatchToProps
    -0.86
    AndroidJUnit
    -0.73
    PreferredItem
    -0.70
    bootstrapcdn
    -0.70
     متعلقه
    -0.66
    AndEndTag
    -0.63
    WithIOException
    -0.62
    thâu
    -0.62
     yder
    -0.62
    vägen
    -0.58
    POSITIVE LOGITS
     FRESH
    1.13
     fresh
    1.11
     Fresh
    1.09
    Fresh
    1.07
    fresh
    1.04
    FRESH
    0.98
     fresca
    0.95
     fres
    0.92
     Fres
    0.89
     frescas
    0.86
    Activations Density 0.029%

    No Known Activations