© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 1969
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences containing statements, questions, and modal verbs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    citenamefont
    -0.19
    <eos>
    -0.18
     ↑
    -0.17
    -0.16
     пожалуйста
    -0.15
     prou
    -0.15
    -0.14
     ніж
    -0.14
    /**
    -0.13
    -------
    -0.13
    POSITIVE LOGITS
    ftagPool
    1.01
    LookAnd
    0.91
    SourceChecksum
    0.89
     للاسماء
    0.85
     ProtoMessage
    0.82
    StoryboardSegue
    0.81
    WriteTagHelper
    0.79
     AssemblyCompany
    0.78
    RTEX
    0.76
    hyrchwyd
    0.74
    Activations Density 0.436%

    No Known Activations