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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 9642
    Prev
    Next
    INDEX
    Explanations

    code-related syntax elements such as parentheses, brackets, and curly braces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ześnie
    -0.57
    TabIndex
    -0.56
    suri
    -0.49
    бва
    -0.49
    DEE
    -0.49
     model
    -0.47
     Bill
    -0.47
    Cita
    -0.47
    Citiți
    -0.46
    skine
    -0.45
    POSITIVE LOGITS
    StoryboardSegue
    0.76
    RetentionPolicy
    0.75
     doInBackground
    0.70
    Collegamenti
    0.70
    awaiter
    0.69
    SequentialGroup
    0.68
     Audiodateien
    0.64
     SwitchCompat
    0.64
     SafeMath
    0.62
    openConnection
    0.62
    Activations Density 0.062%

    No Known Activations