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. 3171
    Prev
    Next
    INDEX
    Explanations

    legal jargon and concepts related to waiver of rights and associated consequences

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

    preceding "those," "these," or "them."

    np_acts-logits-general · gemini-2.0-flash

    demonstrative pronouns and plurals

    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
     resourceCulture
    -0.74
     autorytatywna
    -0.64
    RegressionTest
    -0.55
    zuli
    -0.54
     rootReducer
    -0.51
    SharedCtor
    -0.50
    enumii
    -0.49
    PrototypeOf
    -0.49
    schaft
    -0.49
     MainAxisSize
    -0.49
    POSITIVE LOGITS
     these
    3.57
     These
    3.12
    these
    3.11
    These
    3.03
     THESE
    2.63
    これらの
    2.57
    这些
    2.54
    這些
    2.52
     этих
    2.21
     Эти
    2.11
    Activations Density 2.856%

    No Known Activations