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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1746
    Prev
    Next
    INDEX
    Explanations

    annotations and serialized data formats in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    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
    ValueStyle
    -0.99
     فريبيس
    -0.89
    setVerticalGroup
    -0.85
    ViewInit
    -0.80
     BoxFit
    -0.79
    ruptedException
    -0.78
    DockStyle
    -0.77
    AddTagHelper
    -0.77
     MotionEvent
    -0.77
    onOptions
    -0.76
    POSITIVE LOGITS
     jspb
    0.45
    ↵↵
    0.45
     saisir
    0.44
     Pare
    0.39
     barva
    0.39
    ↵
    0.38
    個性
    0.38
    ніше
    0.37
    ORROW
    0.36
    明
    0.36
    Activations Density 0.013%

    No Known Activations