© 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. 8878
    Prev
    Next
    INDEX
    Explanations

    HTML tags and elements, as well as specific programming syntax

    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
    いく
    -0.35
    DoesNotExist
    -0.33
    География
    -0.32
    imageio
    -0.32
    distinct
    -0.31
    стве
    -0.31
    ਊ
    -0.31
    menta
    -0.31
    notFound
    -0.31
    ukin
    -0.30
    POSITIVE LOGITS
    tagHelperRunner
    1.02
    AddTagHelper
    0.80
    rungsseite
    0.78
     Мексичка
    0.75
     Савезне
    0.75
    OGND
    0.74
     الرياضيه
    0.71
     surla
    0.71
    WriteTagHelper
    0.71
     ModelExpression
    0.69
    Activations Density 0.146%

    No Known Activations