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. 23-GEMMASCOPE-RES-16K
    6. 5667
    Prev
    Next
    INDEX
    Explanations

    code related to Angular imports and dependency injection patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.53
    classpath
    -0.44
     sur
    -0.40
     dne
    -0.39
    íž
    -0.37
    genta
    -0.37
     가
    -0.36
    abadi
    -0.36
    asteroide
    -0.35
     montant
    -0.35
    POSITIVE LOGITS
    StoryboardSegue
    0.92
     المعيارى
    0.83
     Савезне
    0.76
     betweenstory
    0.72
     propOrder
    0.68
    XmlAccessorType
    0.66
    THISDAY
    0.65
     ویکی‌پدیای
    0.65
     WaitForSeconds
    0.64
    MLLoader
    0.62
    Activations Density 0.092%

    No Known Activations