© 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. 34-GEMMASCOPE-RES-16K
    11. 11318
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and judicial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -1.13
     […]
    -1.10
    ↵↵
    -1.01
    <eos>
    -0.97
    -\\
    -0.83
     [...]
    -0.71
    ,\\
    -0.69
     =
    -0.68
    \\
    -0.67
    Continue
    -0.67
    POSITIVE LOGITS
    AddTagHelper
    0.71
     $_"
    0.66
     (\<
    0.61
     $_[
    0.59
     userDao
    0.59
    dafx
    0.59
     myſelf
    0.59
    selben
    0.57
    parsedMessage
    0.57
     $_(
    0.56
    Activations Density 2.804%

    No Known Activations