© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 126
    Prev
    Next
    INDEX
    Explanations

    the structure and organization of academic papers

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

    After "is", "final", "revised", or "organized"

    np_acts-logits-general · gemini-2.0-flash

    organized as follows, final version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     devriez
    -0.61
     "..\..\
    -0.57
    fromnode
    -0.57
     "..\..\..\
    -0.54
     ogni
    -0.54
     cucchiaio
    -0.50
     Alternatively
    -0.49
     pubblici
    -0.48
     capables
    -0.47
     importar
    -0.47
    POSITIVE LOGITS
    脚注の使い方
    0.63
    erees
    0.60
     Accepted
    0.60
    URDAY
    0.59
     typos
    0.58
     revised
    0.58
     transférez
    0.57
    Versión
    0.57
     submitted
    0.56
     Minor
    0.56
    Activations Density 0.130%

    No Known Activations