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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 2410
    Prev
    Next
    INDEX
    Explanations

    references to religious structures and related historical details

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

    Architectural structures and buildings

    np_acts-logits-general · gemini-2.0-flash

    building materials and structures

    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
    رشف
    -0.58
    UserScript
    -0.51
     pooled
    -0.49
    pooled
    -0.48
    opot
    -0.47
    initas
    -0.47
     otomatig
    -0.47
    Personensuche
    -0.47
     Cohn
    -0.45
     Neph
    -0.45
    POSITIVE LOGITS
     structures
    1.40
     building
    1.34
     buildings
    1.32
     structure
    1.31
     Structures
    1.21
    structures
    1.20
     architect
    1.19
     architecture
    1.16
     construction
    1.15
    structure
    1.15
    Activations Density 0.209%

    No Known Activations