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. 14710
    Prev
    Next
    INDEX
    Explanations

    concepts related to improvements, modifications, and discussion topics

    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
     мәкал
    -0.58
     autorytatywna
    -0.55
    DockStyle
    -0.51
     nahilalakip
    -0.51
    localctx
    -0.51
     Administrativna
    -0.50
    Aholisi
    -0.50
    WriteTagHelper
    -0.48
    createNewFile
    -0.48
     AssemblyCulture
    -0.47
    POSITIVE LOGITS
    ArrowToggle
    0.47
    </thead>
    0.40
    Життєпис
    0.37
    MigrationBuilder
    0.33
     "..\..\
    0.33
    pidou
    0.32
     yym
    0.32
     "..\..\..\
    0.30
     defStyleAttr
    0.30
    zegor
    0.29
    Activations Density 0.544%

    No Known Activations