© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2141
    Prev
    Next
    INDEX
    Explanations

    percentage or numeric expressions represented in various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageContext
    -0.47
     traditionally
    -0.37
     Lockwood
    -0.36
    interopRequire
    -0.36
     defe
    -0.36
     central
    -0.35
    ритори
    -0.35
    postsleuth
    -0.35
     gmina
    -0.35
     adult
    -0.35
    POSITIVE LOGITS
    s
    0.46
    webElementXpaths
    0.43
     تضيفلها
    0.43
     spalle
    0.43
    MessageTagHelper
    0.42
    saraba
    0.41
    AutoField
    0.41
    forhold
    0.40
    rungsseite
    0.40
     sereia
    0.40
    Activations Density 0.168%

    No Known Activations