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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1512
    Prev
    Next
    INDEX
    Explanations

    references to nodes and their relationship within a programming or data structure context

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

    "node" in code or text

    np_acts-logits-general · gemini-2.0-flash

    node or nodes

    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
     Dür
    -0.43
     ganha
    -0.41
     American
    -0.40
     the
    -0.40
    Seven
    -0.38
     FirebaseAuth
    -0.38
    ../../
    -0.37
    American
    -0.36
     Gesam
    -0.36
    Gesam
    -0.35
    POSITIVE LOGITS
     Node
    1.20
     node
    1.20
    Node
    1.15
     Nodes
    1.08
     nodes
    1.04
     getNode
    1.02
     NODE
    0.99
    node
    0.96
    getNode
    0.94
    NODE
    0.94
    Activations Density 0.084%

    No Known Activations