© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 773
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation or positive sentiments related to experiences

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

    followed by past-tense verbs

    np_acts-logits-general · gemini-2.0-flash

    we have discussed findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.33
    furt
    -0.33
    žius
    -0.32
    hitheater
    -0.32
    currently
    -0.32
     cintas
    -0.31
    ыгана
    -0.31
     بخ
    -0.31
     Biology
    -0.31
     Obec
    -0.31
    POSITIVE LOGITS
    styleable
    0.58
     resourceCulture
    0.57
    +#+
    0.55
    ftagPool
    0.50
    FormTagHelper
    0.50
     betweenstory
    0.50
     ***!
    0.47
    +:+
    0.47
    providedIn
    0.46
    unknownFields
    0.45
    Activations Density 0.276%

    No Known Activations