© 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. 3009
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate conjunctions or connections in sentences

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

    Phrases with conjunctions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    hook and eye

    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
     externi
    -0.83
     coupable
    -0.53
     superiori
    -0.53
     paraît
    -0.51
     terceiro
    -0.51
    GOTREF
    -0.51
     Préférences
    -0.50
    is
    -0.50
    庁
    -0.50
    ględ
    -0.49
    POSITIVE LOGITS
    ChildScrollView
    0.59
    EnableWeb
    0.59
    ceptre
    0.53
    ollectionView
    0.52
     JpaRepository
    0.52
    aluz
    0.52
     benne
    0.51
    findpost
    0.50
    ArgsConstructor
    0.50
    HIND
    0.50
    Activations Density 0.365%

    No Known Activations