© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5965
    Prev
    Next
    INDEX
    Explanations

    references to parent and child relationships in hierarchical structures

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

    programming-related identifiers and syntax, particularly around parent and ID references in code or data structures.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    +#+
    -0.57
    modelBuilder
    -0.48
    endphp
    -0.48
    wpdb
    -0.46
    TextBoxColumn
    -0.45
     scientifically
    -0.45
     Codable
    -0.45
    reprodu
    -0.43
    ckså
    -0.42
     الحره
    -0.42
    POSITIVE LOGITS
    Parent
    0.71
     parent
    0.68
    getParent
    0.66
     Parent
    0.65
    setParent
    0.63
    parent
    0.62
     getParent
    0.61
    ManyToOne
    0.59
     PARENT
    0.58
    PARENT
    0.57
    Activations Density 0.186%

    No Known Activations