© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 38185
    Prev
    Next
    INDEX
    Explanations

    features and specifications of electronic devices, particularly focusing on their multimedia capabilities

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

    features and specifications

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    rungsseite
    -0.58
     ostavi
    -0.57
    dafx
    -0.53
    BufferException
    -0.46
     okuyayım
    -0.46
     ๆ
    -0.45
    Diweddarwch
    -0.45
    曖昧さ回避
    -0.44
    AutoScale
    -0.44
    Архівовано
    -0.43
    POSITIVE LOGITS
     features
    0.53
    Features
    0.52
     Features
    0.49
    features
    0.47
     FEATURES
    0.47
     functionalities
    0.45
    FEATURES
    0.45
     configurable
    0.45
     Built
    0.45
     boasts
    0.44
    Activations Density 0.030%

    No Known Activations