© 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. 11-GEMMASCOPE-RES-16K
    6. 4767
    Prev
    Next
    INDEX
    Explanations

    programming logic related to key-value pairs and map operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ßerdem
    -0.44
    Rhestr
    -0.44
     informée
    -0.43
    fjspx
    -0.42
    CPtr
    -0.42
    tangentMode
    -0.42
     stück
    -0.41
    Trichloroethane
    -0.41
     inoxidable
    -0.40
     Gottes
    -0.40
    POSITIVE LOGITS
    entrySet
    0.76
    keySet
    0.59
    ContainsKey
    0.53
    Tikang
    0.51
    containsKey
    0.51
    hasOwnProperty
    0.48
    Demografía
    0.46
     keys
    0.45
     Schlüssel
    0.45
    gráfica
    0.45
    Activations Density 0.336%

    No Known Activations