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. 4556
    Prev
    Next
    INDEX
    Explanations

    keywords related to mechanical processes and maintenance

    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
    
    -0.80
    ]")]
    -0.73
     ModelExpression
    -0.71
    migrationBuilder
    -0.64
     COVERAGE
    -0.64
    ilever
    -0.62
     ExecuteAsync
    -0.61
    ArrowToggle
    -0.60
     extérieures
    -0.59
    KommentareTeilen
    -0.59
    POSITIVE LOGITS
    avyzd
    0.52
    TRAILING
    0.50
     recovered
    0.45
     recuper
    0.45
    Referencies
    0.45
     refurb
    0.45
     recover
    0.44
    InstanceOf
    0.44
    WriteTagHelper
    0.44
    BufferException
    0.44
    Activations Density 0.253%

    No Known Activations