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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 10779
    Prev
    Next
    INDEX
    Explanations

    function calls and object method accesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    -0.85
    ING
    -0.74
    ة
    -0.72
    }$)
    -0.66
    makeText
    -0.65
     Kral
    -0.65
    tros
    -0.62
     Mehl
    -0.61
     لينك
    -0.61
    ramanian
    -0.60
    POSITIVE LOGITS
    ")->
    1.45
    ->
    1.41
    ]->
    1.18
    ()->
    1.17
    ))->
    1.15
    ')->
    1.06
    )->
    1.05
     "..\..\
    1.03
     Aja
    1.00
    _->
    0.99
    Activations Density 0.112%

    No Known Activations