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. 2-GEMMASCOPE-RES-16K
    6. 6217
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "out"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [*]
    -0.69
    ьаж
    -0.64
     factura
    -0.58
    twimg
    -0.56
    脚注の使い方
    -0.55
     >=",
    -0.54
    tifully
    -0.53
    Atsauces
    -0.53
    MigrationBuilder
    -0.52
    igte
    -0.52
    POSITIVE LOGITS
     myſelf
    0.93
     itſelf
    0.86
     poffible
    0.77
     Jefus
    0.77
     Majefty
    0.73
     themſelves
    0.71
     becauſe
    0.69
    ſelves
    0.68
     Мексичка
    0.66
     Chriftian
    0.64
    Activations Density 0.173%

    No Known Activations