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. 24-GEMMASCOPE-RES-16K
    6. 14914
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditionality and obligation in the context of governance and social order

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

    Follows "to" or modal verbs

    np_acts-logits-general · gemini-2.0-flash

    infinitive verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ation
    -0.51
    protoimpl
    -0.48
    tagext
    -0.47
     promessa
    -0.46
    Ctor
    -0.45
    OLA
    -0.45
    UserDTO
    -0.45
     Miner
    -0.44
    BooleanField
    -0.44
     nera
    -0.44
    POSITIVE LOGITS
     تضيفلها
    0.65
     ComVisible
    0.64
    AsUp
    0.59
    المناصب
    0.59
    Diwedd
    0.57
     sumpay
    0.56
    Hochspringen
    0.56
    chyma
    0.55
    ttino
    0.55
    #+#
    0.54
    Activations Density 0.046%

    No Known Activations