© 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. 27-GEMMASCOPE-RES-16K
    6. 9707
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software and hardware functionalities, specifically focusing on version control, source management, and engineering systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.63
     صوتيه
    -0.59
    RectangleBorder
    -0.57
    شهاد
    -0.53
    WriteTagHelper
    -0.52
    awaiter
    -0.52
    MigrationBuilder
    -0.50
    principalColumn
    -0.50
    AddTagHelper
    -0.49
    ########.
    -0.48
    POSITIVE LOGITS
     system
    0.41
     systeem
    0.40
     EconPapers
    0.38
     sistema
    0.37
     económico
    0.36
    mær
    0.35
     électrique
    0.34
     systém
    0.34
     alko
    0.34
     getSystem
    0.34
    Activations Density 1.080%

    No Known Activations