© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 3889
    Prev
    Next
    INDEX
    Explanations

    SVG path commands and transformation attributes in vector graphics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.54
    BlockingQueue
    -0.51
     tqdm
    -0.46
    婿
    -0.45
     bombas
    -0.43
    GtkWidget
    -0.42
    spinning
    -0.42
    يج
    -0.42
     diserta
    -0.42
    пис
    -0.42
    POSITIVE LOGITS
    EndContext
    0.97
    fjspx
    0.95
    CGRectMake
    0.88
    HideFlags
    0.83
     AssemblyProduct
    0.79
    ParallelGroup
    0.78
    addGap
    0.77
    kháu
    0.77
     CGRectMake
    0.76
    BeginContext
    0.76
    Activations Density 0.305%

    No Known Activations