© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8871
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical values, likely related to references or IDs in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wirt
    -0.84
     Vivaldi
    -0.83
    dees
    -0.80
    HasBeenSet
    -0.80
    %)$
    -0.79
    continence
    -0.79
    ificance
    -0.78
     изъ
    -0.78
    hhhhhhhh
    -0.77
     góry
    -0.77
    POSITIVE LOGITS
    4
    1.52
     @"/
    1.18
    5
    0.87
     Forty
    0.82
     Vier
    0.79
     THURSDAY
    0.79
    3
    0.78
    4
    0.78
    8
    0.78
     Thurs
    0.78
    Activations Density 1.093%

    No Known Activations