© 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. 31-GEMMASCOPE-RES-16K
    6. 15649
    Prev
    Next
    INDEX
    Explanations

    themes of emotional depth and complexity in narratives and characters

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

    words and phrases that express emotional intensity and strong impact on the reader or listener.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.41
     المهم
    -0.39
    +#+#
    -0.38
    CloseOperation
    -0.35
    下载附件
    -0.34
    oredCriteria
    -0.34
     AssemblyCulture
    -0.33
     importante
    -0.33
     مهم
    -0.32
    AnchorTagHelper
    -0.32
    POSITIVE LOGITS
     surely
    0.73
     truly
    0.73
     sure
    0.73
    truly
    0.69
     unforgettable
    0.66
     Truly
    0.64
     seguramente
    0.64
     deserves
    0.63
    Truly
    0.63
     captiv
    0.61
    Activations Density 0.235%

    No Known Activations