© 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. 28-GEMMASCOPE-RES-16K
    11. 7349
    Prev
    Next
    INDEX
    Explanations

    contractions and forms of negation in writing

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

    Non-English language or references

    np_acts-logits-general · gemini-2.0-flash

    et al

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    package
    -0.40
    Witam
    -0.35
    engagent
    -0.32
    SerializeField
    -0.30
    marginBottom
    -0.28
     megt
    -0.27
    Injectable
    -0.27
    <
    -0.26
     property
    -0.26
    import
    -0.26
    POSITIVE LOGITS
    KommentareTeilen
    0.83
    uxxxx
    0.81
    
    0.80
    ChildScrollView
    0.71
    rungsseite
    0.69
    脚注の使い方
    0.68
     ujednoznacz
    0.68
    帖最后由
    0.67
     متعلقه
    0.64
     surla
    0.64
    Activations Density 0.871%

    No Known Activations