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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12796
    Prev
    Next
    INDEX
    Explanations

    references to app stores and platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     kasarigan
    -0.56
    SourceChecksum
    -0.48
    رشف
    -0.48
    DrawerToggle
    -0.47
    createServer
    -0.45
     dbg
    -0.44
     '\\;'
    -0.42
    endpush
    -0.42
    heitsbild
    -0.42
    dra
    -0.40
    POSITIVE LOGITS
    曖昧さ回避
    0.39
    XMLSchema
    0.39
    BufferException
    0.39
    ContextCompat
    0.38
    :][
    0.37
    Personendaten
    0.37
    pulumi
    0.35
     marketplace
    0.35
     kateg
    0.35
     TimeUnit
    0.34
    Activations Density 1.099%

    No Known Activations