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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 6069
    Prev
    Next
    INDEX
    Explanations

    white spaces or gaps in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.69
     (
    -0.66
     "
    -0.55
    :
    -0.53
    ↵
    -0.52
     /
    -0.49
     and
    -0.49
     ...
    -0.48
     a
    -0.48
     „
    -0.47
    POSITIVE LOGITS
    <bos>
    3.54
     виправивши
    1.40
     Савезне
    1.35
    ’
    1.34
    ########.
    1.30
    '
    1.28
     للمعارف
    1.26
     Мексичка
    1.22
     فريبيس
    1.14
     мәкал
    1.11
    Activations Density 0.211%

    No Known Activations