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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15011
    Prev
    Next
    INDEX
    Explanations

    references to names and identifiers within various contexts

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

    phrases explaining the origin or meaning of a name.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    日閲覧
    -0.40
    writerow
    -0.35
    outWeight
    -0.33
     CreateTagHelper
    -0.33
    andam
    -0.31
     chi̍t
    -0.30
    tagHelper
    -0.30
    Hozzáférés
    -0.29
     ItemStack
    -0.29
    })}\
    -0.29
    POSITIVE LOGITS
     name
    3.30
     names
    2.63
     Name
    2.55
     NAME
    2.41
    name
    2.39
     naam
    2.34
     Namen
    2.30
     이름
    2.27
    Name
    2.17
     Names
    2.14
    Activations Density 1.076%

    No Known Activations