Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 5823
    Prev
    Next
    INDEX
    Explanations

    structural elements and formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unknownFields
    -0.57
    úgó
    -0.53
    (||
    -0.49
    (:,:,
    -0.49
    dataclass
    -0.48
     travaillons
    -0.48
     eventName
    -0.47
     Grazie
    -0.46
     Libros
    -0.44
    日
    -0.44
    POSITIVE LOGITS
     الحره
    1.01
    :✨
    0.93
     الاطلاع
    0.85
     препратки
    0.76
    SBATCH
    0.69
    __':
    0.67
    Datuak
    0.67
     المعيارى
    0.67
    Portail
    0.66
     <<<<<<<<<<<<<<
    0.63
    Activations Density 0.031%

    No Known Activations