© 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. 2-GEMMASCOPE-RES-16K
    6. 8252
    Prev
    Next
    INDEX
    Explanations

    references to a significant size or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.60
     ujednoznacz
    -0.57
     disambiguazione
    -0.53
    chartInstance
    -0.52
     iſt
    -0.48
    +#+
    -0.48
     startIndex
    -0.48
     createSprite
    -0.47
    Попис
    -0.46
     desto
    -0.46
    POSITIVE LOGITS
     enormous
    0.92
     huge
    0.85
     Huge
    0.84
    Huge
    0.81
     enormes
    0.75
    huge
    0.73
    ormous
    0.71
     immense
    0.68
     énorme
    0.67
     enorme
    0.64
    Activations Density 0.125%

    No Known Activations