© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11163
    Prev
    Next
    INDEX
    Explanations

    elements of code and programming structures, especially those related to data handling and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.75
    InitVars
    -0.69
    parsedMessage
    -0.68
     ddelweddau
    -0.63
     كومونز
    -0.62
    +#+#
    -0.60
    principalTable
    -0.59
     AssemblyCulture
    -0.59
     nakalista
    -0.59
     zobac
    -0.56
    POSITIVE LOGITS
    뀜
    0.50
     utility
    0.46
    ckle
    0.42
    })*/
    0.42
     SDI
    0.41
     syste
    0.40
     Yoko
    0.40
     webs
    0.40
     sof
    0.40
     utilities
    0.39
    Activations Density 0.508%

    No Known Activations