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. 3817
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the term "utils."

    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
     plomb
    -0.57
    Gizmos
    -0.54
    pstmt
    -0.53
    arot
    -0.53
     Null
    -0.52
     Prius
    -0.52
    MapView
    -0.51
     caution
    -0.51
    льга
    -0.50
     podido
    -0.49
    POSITIVE LOGITS
     nahilalakip
    0.91
     wounded
    0.85
     يتيمه
    0.85
     injured
    0.82
    出版年
    0.82
     raiſ
    0.79
    Injured
    0.75
     xmlns
    0.75
    UnusedPrivate
    0.75
    protoimpl
    0.73
    Activations Density 0.036%

    No Known Activations