Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 3858
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     olyan
    -0.44
    engah
    -0.44
    pota
    -0.43
    ynia
    -0.43
    ोंने
    -0.43
    ichter
    -0.43
    engesch
    -0.43
    hing
    -0.40
    ilage
    -0.40
    ń
    -0.40
    POSITIVE LOGITS
     незавершена
    1.04
    DockStyle
    0.84
    Искәрмәләр
    0.81
    ANTLR
    0.79
    enumii
    0.77
    enumi
    0.75
    MigrationBuilder
    0.74
    iastes
    0.73
     snippetHide
    0.72
    GRANTED
    0.68
    Activations Density 0.308%

    No Known Activations