© 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. 7-GEMMASCOPE-RES-16K
    6. 9852
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and symbols related to mathematics and physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.98
    PickerController
    -0.85
    
    -0.85
    Jum
    -0.79
    gonic
    -0.78
     Camara
    -0.76
     Ebers
    -0.74
     Toma
    -0.73
     GNA
    -0.70
    er
    -0.68
    POSITIVE LOGITS
     Haf
    1.13
     Huf
    1.09
     Sif
    1.06
     Mif
    1.02
     waf
    0.99
     Kaf
    0.98
     Nef
    0.98
     Duf
    0.98
    Bif
    0.97
     Hef
    0.97
    Activations Density 1.371%

    No Known Activations