© 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. 12-GEMMASCOPE-RES-16K
    6. 5670
    Prev
    Next
    INDEX
    Explanations

    programming constructs and functions related to mapping data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newUser
    -0.53
    CloseOperation
    -0.47
     customerId
    -0.46
    issen
    -0.45
     gouden
    -0.44
     protagonista
    -0.44
    withCredentials
    -0.43
    non
    -0.43
    primo
    -0.42
     jerawat
    -0.42
    POSITIVE LOGITS
     map
    1.88
     Map
    1.84
    Map
    1.71
     maps
    1.62
     Maps
    1.58
    map
    1.57
     MAP
    1.48
    Maps
    1.38
    MAP
    1.35
    getMap
    1.35
    Activations Density 0.056%

    No Known Activations