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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 37-GEMMASCOPE-RES-16K
    6. 1195
    Prev
    Next
    INDEX
    Explanations

    code related to programming functions and scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.59
    ágenes
    -0.59
     BoxDecoration
    -0.56
    ]?.
    -0.54
    mybatisplus
    -0.54
     gyhoeddwyd
    -0.54
    onedDateTime
    -0.53
     defStyleAttr
    -0.52
    makeConstraints
    -0.51
     EconPapers
    -0.50
    POSITIVE LOGITS
    jQuery
    0.64
     jQuery
    0.64
    console
    0.63
    alert
    0.60
     $.
    0.59
     alert
    0.54
    undefined
    0.54
    $('#
    0.54
    $("#
    0.53
    JSON
    0.51
    Activations Density 0.663%

    No Known Activations