Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 1639
    Prev
    Next
    INDEX
    Explanations

    structured data and references within technical documents

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

    Numbers within or related to citations/references

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by punctuation or 'is'

    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
     bezeichneter
    -0.42
     raiſ
    -0.41
     anſ
    -0.41
     ſte
    -0.39
     ſur
    -0.39
    ']?>
    -0.38
     ſt
    -0.38
     poffible
    -0.38
     leſs
    -0.37
     ſta
    -0.37
    POSITIVE LOGITS
    WaitGroup
    0.48
    Parcelize
    0.46
    uple
    0.46
     Waray
    0.45
    etCode
    0.45
    backtracking
    0.44
    openzeppelin
    0.44
    terase
    0.44
     MainAxisSize
    0.42
    lccn
    0.42
    Activations Density 1.722%

    No Known Activations