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. 3-GEMMASCOPE-RES-16K
    6. 10148
    Prev
    Next
    INDEX
    Explanations

    mathematical or technical symbols and terms related to formatting or structure

    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
     Theſe
    -0.92
    WidgetItem
    -0.70
    })->
    -0.69
     RSSSF
    -0.68
    sentry
    -0.65
     Ferner
    -0.63
    houette
    -0.63
     CiNii
    -0.61
    InteropServices
    -0.61
     թվ
    -0.61
    POSITIVE LOGITS
    SqlSession
    0.65
    AnimationsModule
    0.55
    CppMethod
    0.50
    IUrlHelper
    0.49
    -(
    0.49
    -
    0.48
    -{
    0.47
    🏾
    0.46
    🏽
    0.44
    -.
    0.43
    Activations Density 0.262%

    No Known Activations