Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 58437
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "flu" in various contexts

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

    fl words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.64
    subpackage
    -0.59
    extAlignment
    -0.56
     nahilalakip
    -0.52
     varandra
    -0.52
    multirow
    -0.52
     disponibilités
    -0.51
    UVWXYZ
    -0.51
    もしれない
    -0.50
     πρόσ
    -0.50
    POSITIVE LOGITS
     fl
    1.99
     Fl
    1.99
    Fl
    1.81
    fl
    1.51
     Flur
    0.92
     flushing
    0.85
     Flushing
    0.84
     FLO
    0.79
     flush
    0.74
     Flü
    0.73
    Activations Density 0.009%

    No Known Activations