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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 10647
    Prev
    Next
    INDEX
    Explanations

    specific formatting and structural elements in documents, such as LaTeX commands and citations

    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
    CDCl
    -0.42
    ➋
    -0.39
     similar
    -0.34
     choice
    -0.34
     tø
    -0.34
    gridLayout
    -0.34
     plate
    -0.33
     less
    -0.32
     part
    -0.31
    īg
    -0.31
    POSITIVE LOGITS
     يتيمه
    0.96
    principalColumn
    0.73
    LookAnd
    0.65
    NameInMap
    0.63
    IUrlHelper
    0.62
     MainAxisSize
    0.58
     Wikimedijinoj
    0.54
    hyrchwyd
    0.54
    IndentedString
    0.53
    WithIOException
    0.52
    Activations Density 1.330%

    No Known Activations