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. 12-GEMMASCOPE-RES-16K
    6. 5555
    Prev
    Next
    INDEX
    Explanations

    various formatting and referencing styles commonly found in academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.62
     виправивши
    -0.60
     ſever
    -0.60
     themſelves
    -0.58
     Monfieur
    -0.56
     useDispatch
    -0.55
    ("")]
    
    -0.55
     juſ
    -0.54
    choly
    -0.54
     ſch
    -0.54
    POSITIVE LOGITS
     kasarigan
    0.84
    ftagPool
    0.64
    CreateModel
    0.63
     autorytatywna
    0.59
    ClientSize
    0.59
    脚注の使い方
    0.58
    깥
    0.58
     "..\..\..\
    0.53
     invokingState
    0.53
    InstrumentedTest
    0.52
    Activations Density 0.126%

    No Known Activations