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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10475
    Prev
    Next
    INDEX
    Explanations

    elements related to opportunities for learning and engagement in technical or scientific contexts

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

    suggesting firsthand or direct experience

    np_acts-logits-general · gemini-2.0-flash

    direct personal experience

    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
    脚注の使い方
    -0.74
    tvguidetime
    -0.61
    Rüyada
    -0.59
    ParallelGroup
    -0.59
     Normdatei
    -0.57
    principalColumn
    -0.56
    ⓧ
    -0.56
    endency
    -0.55
    曖昧さ回避
    -0.55
     NUKAT
    -0.55
    POSITIVE LOGITS
     firsthand
    1.96
     direct
    1.35
     personally
    1.30
     directly
    1.29
    directly
    1.23
    Direct
    1.20
     langsung
    1.18
     Direct
    1.16
    direct
    1.14
     trực
    1.13
    Activations Density 0.333%

    No Known Activations