© 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. 257
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditionality or limitations in statements

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

    Follows "even", "given", "due" or "based"

    np_acts-logits-general · gemini-2.0-flash

    circumstances and conditions

    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
     Monfieur
    -0.51
     myſelf
    -0.50
     Majefty
    -0.50
     Houſe
    -0.48
    CrossRef
    -0.47
     Verſ
    -0.46
    .*")]
    -0.46
    </>
    -0.45
     ſeveral
    -0.44
     ſche
    -0.44
    POSITIVE LOGITS
    MENAFN
    0.59
    fromnode
    0.55
    PreferredItem
    0.52
    NoteOnEvent
    0.49
     onPostExecute
    0.46
     مشين
    0.44
    ſt
    0.42
    ándola
    0.41
     její
    0.40
     سكانية
    0.40
    Activations Density 1.390%

    No Known Activations