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. 11-GEMMASCOPE-RES-16K
    6. 2059
    Prev
    Next
    INDEX
    Explanations

    structural elements and function definitions in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    енча
    -0.61
    labus
    -0.45
     primary
    -0.44
     Lewis
    -0.43
     behaviour
    -0.42
    –
    -0.41
     zdarma
    -0.41
     steder
    -0.41
    جستارهای
    -0.40
     input
    -0.40
    POSITIVE LOGITS
    TagMode
    1.14
    ValueStyle
    1.06
    ButterKnife
    1.06
    fjspx
    1.03
    SequentialGroup
    1.03
    BeginContext
    0.97
    CGRectMake
    0.97
    ConstraintMaker
    0.97
    ParallelGroup
    0.94
     Exacts
    0.91
    Activations Density 0.169%

    No Known Activations