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. 3-GEMMASCOPE-RES-16K
    6. 8576
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.68
     Avic
    -0.59
    RenderAtEndOf
    -0.57
    interopRequire
    -0.56
    StructEnd
    -0.55
     puissiez
    -0.55
     pinulongan
    -0.54
    وعة
    -0.53
    éroport
    -0.53
     NDEBUG
    -0.52
    POSITIVE LOGITS
    XMLSchema
    0.68
    TagMode
    0.65
    SourceChecksum
    0.63
    #+#
    0.60
     resourceCulture
    0.60
    GraphicsUnit
    0.57
    AddHtmlAttribute
    0.56
    WillAppear
    0.54
    logrus
    0.53
    +:+
    0.53
    Activations Density 1.916%

    No Known Activations