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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 57811
    Prev
    Next
    INDEX
    Explanations

    domain names associated with educational and organizational institutions

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

    email addresses and urls `.de .edu .com .it`

    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
    Autoritní
    -0.77
     snippetHide
    -0.75
    RegressionTest
    -0.65
    ########.
    -0.65
    Искәрмәләр
    -0.59
    tvguidetime
    -0.59
     Signalez
    -0.54
    .*")]
    -0.52
    Espèce
    -0.51
    awtextra
    -0.51
    POSITIVE LOGITS
     arşivlendi
    0.61
    .
    0.49
     Erst
    0.44
    Distances
    0.38
    subplots
    0.38
     uğ
    0.38
     Agreements
    0.37
     Agreement
    0.37
     Couples
    0.37
    errHandler
    0.36
    Activations Density 0.003%

    No Known Activations