© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10693
    Prev
    Next
    INDEX
    Explanations

    patterns related to error code documentation and HTML structure

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

    Error codes or messages

    np_acts-logits-general · gemini-2.0-flash

    error code : AVERROR

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -0.68
     defaultstate
    -0.68
    ItemBackground
    -0.63
    ++
    
    -0.55
    HideFlags
    -0.55
     Photocase
    -0.55
     jsPsych
    -0.54
    GTCX
    -0.54
    MultipartFile
    -0.53
     saites
    -0.53
    POSITIVE LOGITS
     iconLine
    0.41
    SuppressLint
    0.38
    esistenza
    0.38
    entado
    0.36
     is
    0.35
    ButterKnife
    0.34
    RemoveField
    0.34
     Beteiligung
    0.34
     controllare
    0.34
    nhung
    0.34
    Activations Density 1.108%

    No Known Activations