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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14888
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and regression modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exec
    -0.40
    ########.
    -0.38
     damit
    -0.35
    optarg
    -0.35
    账
    -0.35
    AnchorTagHelper
    -0.35
     gres
    -0.34
    exec
    -0.34
     StringTokenizer
    -0.34
    Strateg
    -0.33
    POSITIVE LOGITS
     AspNetCore
    0.56
     AssemblyVersion
    0.54
     mål
    0.52
    目标
    0.52
    IUrlHelper
    0.49
     goal
    0.49
     CanadaChoose
    0.47
    Tembelea
    0.47
     objectif
    0.47
     mục
    0.47
    Activations Density 0.917%

    No Known Activations