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. 22-GEMMASCOPE-RES-16K
    6. 11099
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistical representations in the text

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

    "100" followed by a number

    np_acts-logits-general · gemini-2.0-flash

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __))
    -0.61
    ']))
    
    -0.60
    Спасылкі
    -0.59
    '])){
    
    -0.58
    >--}}
    -0.57
    \{\\
    -0.56
     محفوظة
    -0.56
    }*/
    
    -0.56
    '])->
    -0.56
    ghua
    -0.55
    POSITIVE LOGITS
    gridx
    0.63
    Bioaccumulative
    0.59
    Eloquent
    0.56
    SpringRunner
    0.54
    dpi
    0.54
    GEBURTSDATUM
    0.54
    urably
    0.53
    mbler
    0.53
     propOrder
    0.51
    +#+#
    0.51
    Activations Density 0.249%

    No Known Activations