© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14140
    Prev
    Next
    INDEX
    Explanations

    JSON key-value pairs related to data type definitions

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

    "type": followed by a string

    np_acts-logits-general · gemini-2.0-flash

    the key 'type'

    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
    endphp
    -0.77
     bénévol
    -0.61
    UnitTesting
    -0.61
    postsleuth
    -0.60
    ſcher
    -0.59
    ьажоргаш
    -0.57
    __":
    
    -0.56
    RUnlock
    -0.56
     mengumpulkan
    -0.55
    archiviato
    -0.54
    POSITIVE LOGITS
     type
    1.39
     Type
    1.37
    Type
    1.31
     TYPE
    1.26
    type
    1.26
    TYPE
    1.16
     types
    1.09
    getType
    1.04
     getType
    1.01
    stype
    0.99
    Activations Density 0.237%

    No Known Activations