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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8538
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and statistical terms related to intervals and ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical notation for intervals in LaTeX format, particularly expressions involving brackets like "]" and "[" with coordinates.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.52
     picioare
    -0.45
     thereunder
    -0.40
    Lähteet
    -0.38
    ANNELS
    -0.35
     Públicas
    -0.35
     merit
    -0.35
    
    -0.34
     kysy
    -0.34
     rimasto
    -0.33
    POSITIVE LOGITS
     interval
    0.75
     AssemblyVersion
    0.69
     Interval
    0.66
    interval
    0.66
     intervalo
    0.63
    fjspx
    0.57
     autorytatywna
    0.57
    Interval
    0.56
     intervals
    0.56
    区间
    0.56
    Activations Density 0.997%

    No Known Activations