© 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. 14654
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to electrical and electronic components and devices

    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
    principalColumn
    -0.50
     nahilalakip
    -0.50
    OGND
    -0.49
    SourceChecksum
    -0.46
    Viungo
    -0.44
     ویکی‌پدی
    -0.43
     onAnimation
    -0.43
     Infórmanos
    -0.41
    WritableDatabase
    -0.41
    AnchorTagHelper
    -0.39
    POSITIVE LOGITS
     electric
    2.91
     electrical
    2.77
     Electric
    2.59
     ELECTRIC
    2.53
    electric
    2.50
    Electric
    2.50
     Electrical
    2.45
     elect
    2.39
    Electrical
    2.36
    electrical
    2.36
    Activations Density 1.352%

    No Known Activations