© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11020
    Prev
    Next
    INDEX
    Explanations

    themes related to contractual and legal obligations

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

    Follows "without," "on," or "at."

    np_acts-logits-general · gemini-2.0-flash

    notice with condition or time

    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
    enumii
    -0.58
    enumi
    -0.51
    Parcelize
    -0.48
    BooleanField
    -0.47
     sag
    -0.46
    Reality
    -0.46
     elect
    -0.45
     alma
    -0.45
     op
    -0.44
    Enllaces
    -0.43
    POSITIVE LOGITS
     notice
    1.62
    notice
    1.39
     Notice
    1.35
    Notice
    1.24
     NOTICE
    1.20
     notices
    1.16
     notification
    1.09
     warning
    1.07
    NOTICE
    1.05
     aviso
    1.02
    Activations Density 0.118%

    No Known Activations