© 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. 1143
    Prev
    Next
    INDEX
    Explanations

    headers or introductory tags in the document

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

    Tokens preceding or following asterisks ("*")

    np_acts-logits-general · gemini-2.0-flash

    end of line wishes or specialized terms

    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
    ,
    -0.62
    mybatisplus
    -0.62
     المعيارى
    -0.61
    -
    -0.61
    .
    -0.61
     in
    -0.60
     su
    -0.58
     mergeFrom
    -0.57
     company
    -0.55
     par
    -0.53
    POSITIVE LOGITS
     myſelf
    1.14
    ſelves
    1.09
     ainfi
    1.08
     ſind
    1.07
     auffi
    1.05
     purpoſe
    1.05
     ་་
    1.04
     reaſon
    1.03
    ſelf
    1.03
     Houſe
    1.01
    Activations Density 0.366%

    No Known Activations