© 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. 28-GEMMASCOPE-RES-16K
    11. 8347
    Prev
    Next
    INDEX
    Explanations

    closing braces in programming code

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

    Code blocks ending with closing brackets

    np_acts-logits-general · gemini-2.0-flash

    else conditional blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.61
    ToScroll
    -0.59
     AssemblyVersion
    -0.57
     lenker
    -0.57
    IUrlHelper
    -0.56
    帖最后由
    -0.56
    tvguidetime
    -0.54
    存于互联网档案馆
    -0.52
    المناصب
    -0.52
    mergeFrom
    -0.50
    POSITIVE LOGITS
    ↵↵
    0.55
    ↵
    0.54
    </h4>
    0.45
     So
    0.42
     This
    0.40
     In
    0.39
    </blockquote>
    0.38
     Hopefully
    0.38
    </h3>
    0.37
     If
    0.37
    Activations Density 0.209%

    No Known Activations