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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3138
    Prev
    Next
    INDEX
    Explanations

    code block structures and flow control statements

    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
    PerformLayout
    -0.57
    nodoc
    -0.56
     Antioch
    -0.49
    SharedCtor
    -0.48
    TypedArray
    -0.47
    shame
    -0.45
     Deliver
    -0.45
     Pro
    -0.45
    Avan
    -0.44
    DEZ
    -0.43
    POSITIVE LOGITS
    matchCondition
    0.78
     متعلقه
    0.73
    tură
    0.68
    isable
    0.66
     CreateTagHelper
    0.65
    typeorm
    0.64
    AddTagHelper
    0.59
     Приступљено
    0.56
    Personendaten
    0.56
    sterious
    0.56
    Activations Density 0.035%

    No Known Activations