© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117445
    Prev
    Next
    INDEX
    Explanations

    references to alarm-related concepts in the context of programming

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

    push notifications

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     adaptée
    -0.23
     Flasche
    -0.22
     tantangan
    -0.22
     colored
    -0.21
     Cassel
    -0.21
    を見せて
    -0.21
     marks
    -0.20
    ObjectId
    -0.20
     Française
    -0.20
     widać
    -0.20
    POSITIVE LOGITS
     betweenstory
    0.76
    URLException
    0.72
    +#+#
    0.71
    tvguidetime
    0.69
     صوتيه
    0.66
    Diweddarwch
    0.66
     zwiſchen
    0.65
     noDo
    0.65
    AddTagHelper
    0.64
    PerformLayout
    0.64
    Activations Density 0.009%

    No Known Activations