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. 13-GEMMASCOPE-RES-16K
    6. 12285
    Prev
    Next
    INDEX
    Explanations

    sections of text that begin and end

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IContainer
    -0.84
    WithIOException
    -0.73
    Попис
    -0.72
    DockStyle
    -0.71
     calendriers
    -0.71
    انيف
    -0.70
    ImageContext
    -0.68
    MLLoader
    -0.68
    providedIn
    -0.65
    UnknownFieldSet
    -0.64
    POSITIVE LOGITS
     required
    0.63
     requirements
    0.49
     requirement
    0.48
     onCreateView
    0.47
     Required
    0.46
    sification
    0.46
     valid
    0.46
     requerido
    0.44
     ensure
    0.43
    Required
    0.42
    Activations Density 0.109%

    No Known Activations