© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12717
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax and structure

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

    Code snippets involving reading and retrieval

    np_acts-logits-general · gemini-2.0-flash

    reading or retrieving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    executeUpdate
    -0.49
    saraba
    -0.45
     setValue
    -0.43
     addNew
    -0.43
    Installing
    -0.43
    estinos
    -0.43
     setObject
    -0.42
     setError
    -0.42
    AddNew
    -0.41
     addUser
    -0.41
    POSITIVE LOGITS
     retrieval
    1.20
     retrieve
    1.13
     retrieving
    1.07
     querying
    0.98
     query
    0.98
     retrieved
    0.95
     Retrieval
    0.95
    retrieve
    0.94
     read
    0.93
     fetch
    0.93
    Activations Density 0.784%

    No Known Activations