© 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. 16-GEMMASCOPE-RES-16K
    6. 6814
    Prev
    Next
    INDEX
    Explanations

    terms related to testing and measurement in a technical or scientific context

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

    followed by prepositions or "is"

    np_acts-logits-general · gemini-2.0-flash

    technical terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -1.38
     Савезне
    -1.19
    脚注の使い方
    -1.16
     autorytatywna
    -1.13
    rungsseite
    -1.12
    __':
    
    -1.11
    WithIOException
    -1.11
     Roskov
    -1.10
     }}"></
    -1.08
    Vidite
    -1.06
    POSITIVE LOGITS
    ,
    0.62
     is
    0.59
     for
    0.59
     in
    0.58
    .
    0.58
     tersebut
    0.57
     of
    0.54
     to
    0.54
     stesso
    0.53
     that
    0.53
    Activations Density 1.778%

    No Known Activations