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. 20-GEMMASCOPE-RES-16K
    6. 15752
    Prev
    Next
    INDEX
    Explanations

    references to specific instructions or guidelines within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers or enumeration

    np_acts-logits-general · gemini-2.0-flash

    numbered sections and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.79
     للمعارف
    -0.77
     Roskov
    -0.75
     disambiguazione
    -0.70
    +:+
    -0.68
    }();
    -0.68
    TemporalType
    -0.67
    afficheront
    -0.65
     Touchable
    -0.65
    期刊论文
    -0.63
    POSITIVE LOGITS
    第
    1.20
     #
    1.17
     Nummer
    0.93
     №
    0.92
     Part
    0.91
    #
    0.91
     Option
    0.90
     Section
    0.89
     Episode
    0.89
     Item
    0.88
    Activations Density 2.799%

    No Known Activations