© 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. 20-GEMMASCOPE-RES-16K
    6. 14447
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software setup and development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jstor
    -0.54
     CanadaChoose
    -0.53
    évaluateur
    -0.45
    eclipse
    -0.45
    kuuta
    -0.43
     EconPapers
    -0.43
    CodeAttribute
    -0.42
     Bod
    -0.40
     Raleigh
    -0.40
    blockList
    -0.40
    POSITIVE LOGITS
    vue
    0.81
    Vue
    0.75
     Vue
    0.72
     vue
    0.54
    Izvori
    0.48
     ProtoMessage
    0.47
    oa̍t
    0.45
    ngdoc
    0.44
     PeEnEo
    0.44
    Попис
    0.43
    Activations Density 0.070%

    No Known Activations