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. 18-GEMMASCOPE-RES-16K
    6. 14725
    Prev
    Next
    INDEX
    Explanations

    terms related to ecclesiastical hierarchy and structures

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

    starting with "Arch" or "arch"

    np_acts-logits-general · gemini-2.0-flash

    arch followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     détach
    -0.69
     judiciaire
    -0.62
     vété
    -0.58
    InlineData
    -0.57
     nourrir
    -0.56
    AccessorTable
    -0.56
     plongée
    -0.56
     étions
    -0.55
     juger
    -0.55
     téléphonique
    -0.54
    POSITIVE LOGITS
     ARCH
    1.00
     arch
    0.91
     Arch
    0.90
    Arch
    0.88
     arches
    0.80
    arch
    0.77
    ARCH
    0.75
     Arches
    0.73
     archi
    0.70
     Archibald
    0.70
    Activations Density 0.092%

    No Known Activations