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. 20-GEMMASCOPE-RES-131K
    6. 64620
    Prev
    Next
    INDEX
    Explanations

    names and references related to familial and relational connections, particularly emphasizing lineage and relationships in text

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

    ion or portion bonding

    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
     AssemblyProduct
    -0.55
    +#+
    -0.53
    ########.
    -0.49
    
    -0.49
    ropractic
    -0.48
     textStatus
    -0.48
    SAFETY
    -0.47
     SAFETY
    -0.47
    safety
    -0.47
    Zacks
    -0.47
    POSITIVE LOGITS
     TextAppearance
    0.40
     ब्रेकडाउन
    0.35
    quelize
    0.34
    forChild
    0.33
    wakili
    0.33
     trúc
    0.33
    avut
    0.32
     bedingt
    0.32
    Tikang
    0.31
    läufig
    0.31
    Activations Density 0.243%

    No Known Activations