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. 14-GEMMASCOPE-RES-16K
    6. 4317
    Prev
    Next
    INDEX
    Explanations

    topics related to digital technology and social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bibinfo
    -0.60
    ably
    -0.53
     isNameExpr
    -0.53
    himp
    -0.48
    bibfield
    -0.48
     smoke
    -0.48
     said
    -0.46
    HISTOR
    -0.44
    seins
    -0.43
     gas
    -0.43
    POSITIVE LOGITS
     referenties
    0.76
    GOTREF
    0.70
    참고
    0.69
     kasarigan
    0.68
    windowFixed
    0.67
     ostavi
    0.66
    mergeFrom
    0.66
    bootstrapcdn
    0.62
    SupportActionBar
    0.62
    MemoryWarning
    0.62
    Activations Density 0.241%

    No Known Activations