Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6603
    Prev
    Next
    INDEX
    Explanations

    structural elements and references in a document, such as sections, chapters, and specific aim points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.44
     popular
    -0.42
     lentejuelas
    -0.41
    Turkish
    -0.40
    ksesta
    -0.40
    kregen
    -0.39
     neuem
    -0.39
    Cyfeiriadau
    -0.39
     Dernière
    -0.38
    tagez
    -0.38
    POSITIVE LOGITS
    ViewFeatures
    0.49
     Normdatei
    0.49
    Portail
    0.45
    */].
    0.45
    InputBorder
    0.44
    WireFormatLite
    0.43
    JsonHelper
    0.43
    OrNil
    0.43
    TemporalType
    0.42
     Roskov
    0.42
    Activations Density 0.878%

    No Known Activations