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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 407
    Prev
    Next
    INDEX
    Explanations

    function calls and their syntax in programming language code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code and error messages

    np_acts-logits-general · gemini-2.0-flash

    closing parenthesis followed by method calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtate
    -0.43
     houſe
    -0.42
     pleaſure
    -0.41
     ftate
    -0.38
     الحره
    -0.38
     ſeveral
    -0.36
     Jefus
    -0.36
     ſon
    -0.36
     ſmall
    -0.36
     Majefty
    -0.33
    POSITIVE LOGITS
     JScrollPane
    0.62
     >::
    0.59
     CURLOPT
    0.59
    fjspx
    0.59
    HasColumnType
    0.58
    tonsoft
    0.56
     оригіналу
    0.54
    HasForeignKey
    0.53
     PicClick
    0.53
    invokeLater
    0.52
    Activations Density 0.193%

    No Known Activations