© 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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 14785
    Prev
    Next
    INDEX
    Explanations

    references and discussions about health-related issues, particularly deficiencies in populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.60
    setVerticalGroup
    -0.55
    ammans
    -0.48
     CURIAM
    -0.46
    EncBinary
    -0.42
    醐
    -0.41
    MessageTagHelper
    -0.41
    TagMode
    -0.41
    AddHtmlAttribute
    -0.41
    tagHelperRunner
    -0.40
    POSITIVE LOGITS
     still
    4.38
    still
    3.86
    Still
    3.67
     Still
    3.53
     STILL
    3.20
     fortfarande
    3.11
     ftill
    3.09
     masih
    3.05
     todavía
    3.05
    STILL
    2.98
    Activations Density 2.658%

    No Known Activations