© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1447
    Prev
    Next
    INDEX
    Explanations

    references to time-related concepts or events

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

    Followed by numbers or other special characters

    np_acts-logits-general · gemini-2.0-flash

    numbers and specific words

    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
     незавершена
    -0.52
     Numerade
    -0.52
     Мексичка
    -0.44
    outSlope
    -0.44
    ulongan
    -0.43
    Geplaatst
    -0.42
    ustimmung
    -0.40
    łgor
    -0.40
     kaarangay
    -0.40
     aufzu
    -0.40
    POSITIVE LOGITS
    kheim
    0.44
     MainAxisSize
    0.41
    ớm
    0.39
    IntoConstraints
    0.39
    ſelves
    0.39
    Vidite
    0.38
     виправивши
    0.38
     taskId
    0.38
    évaluateur
    0.38
    UpInside
    0.38
    Activations Density 2.035%

    No Known Activations