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. 7815
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mathematical concepts, particularly those involving transformations and entropy

    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
    ArrowToggle
    -0.60
     ब्रेकडाउन
    -0.51
    әрмәләр
    -0.51
    Жен
    -0.49
    valbard
    -0.49
    ément
    -0.48
     ProtoMessage
    -0.48
     gyhoeddwyd
    -0.48
    UrlResolution
    -0.47
    Jîn
    -0.47
    POSITIVE LOGITS
     createSlice
    0.37
     понятно
    0.36
     Schatz
    0.36
    setContentView
    0.35
    findpost
    0.34
     leveren
    0.33
     liggen
    0.32
     szint
    0.31
     Leistung
    0.31
     Sexton
    0.31
    Activations Density 1.652%

    No Known Activations