© 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. 72579
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and their treatments, particularly involving tissue and bonding

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

    dentin bonding and bleeding

    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
    AndroidJUnit
    -0.45
    tagHelperRunner
    -0.38
    anwal
    -0.35
    btnBack
    -0.33
     omelette
    -0.33
    Abandon
    -0.32
    antwo
    -0.32
     Broth
    -0.31
     ấm
    -0.31
    stdc
    -0.31
    POSITIVE LOGITS
    Autoritní
    0.60
     الرياضيه
    0.57
    SourceChecksum
    0.54
     <=",
    0.51
     <<<<<<<<<<<<<<
    0.50
     swam
    0.46
    تمبر
    0.45
     OFDb
    0.45
     mecánica
    0.43
    FromNib
    0.42
    Activations Density 0.029%

    No Known Activations