© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11082
    Prev
    Next
    INDEX
    Explanations

    the word "often" and its variations in contexts discussing frequency or regularity

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

    "often" or its synonyms

    np_acts-logits-general · gemini-2.0-flash

    often

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deinit
    -0.52
    IntoConstraints
    -0.50
    shiro
    -0.49
    瘩
    -0.48
    IContainer
    -0.48
     Schild
    -0.48
    yelidikan
    -0.46
    новништво
    -0.45
     isole
    -0.45
    anzug
    -0.44
    POSITIVE LOGITS
     often
    1.10
    often
    1.05
    Often
    0.98
     Often
    0.96
     frequently
    0.91
    frequently
    0.90
     kerap
    0.81
     často
    0.79
     sering
    0.79
     souvent
    0.79
    Activations Density 0.059%

    No Known Activations