© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8814
    Prev
    Next
    INDEX
    Explanations

    terms related to stability and support in mechanical or physical devices

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

    meaning "fixed" or "steady."

    np_acts-logits-general · gemini-2.0-flash

    position and stability

    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
     Administrativna
    -0.57
    RTDA
    -0.41
    contentLoaded
    -0.41
    Notae
    -0.40
    зія
    -0.40
     purpoſe
    -0.40
     kasarigan
    -0.40
     preſ
    -0.39
     Maori
    -0.38
     transfieras
    -0.38
    POSITIVE LOGITS
    bewerken
    0.57
     nakalista
    0.54
    ValueGenerated
    0.52
     Numerade
    0.48
    twimg
    0.46
    TypedDataSet
    0.45
    下载附件
    0.43
     sostener
    0.43
     sostiene
    0.42
    ViewInit
    0.42
    Activations Density 0.336%

    No Known Activations