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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 337
    Prev
    Next
    INDEX
    Explanations

    technical terms related to audio equipment and their specifications

    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
    crollView
    -0.30
     act
    -0.28
     template
    -0.27
     נוס
    -0.26
     lex
    -0.26
     threatening
    -0.26
     sere
    -0.26
     sword
    -0.26
    班
    -0.25
     def
    -0.25
    POSITIVE LOGITS
     surla
    1.04
    parsedMessage
    0.91
     transférez
    0.77
    GEBURTSDATUM
    0.75
    SharedDtor
    0.72
    argout
    0.72
    脚注の使い方
    0.71
    цездатний
    0.71
    woofer
    0.70
     يتيمه
    0.70
    Activations Density 0.122%

    No Known Activations