© 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. 860
    Prev
    Next
    INDEX
    Explanations

    technical terms related to genetics and biological processes

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

    immediately following sentence beginnings

    np_acts-logits-general · gemini-2.0-flash

    verb phrases and past tense

    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
    Lmfao
    -0.65
     leveraging
    -0.61
    tvguidetime
    -0.60
    存于互联网档案馆
    -0.57
     Référence
    -0.54
    Jeografia
    -0.53
     Lmao
    -0.51
     Мексичка
    -0.51
    TLDR
    -0.50
    potentially
    -0.50
    POSITIVE LOGITS
     yesterday
    0.59
     Yesterday
    0.58
     speakers
    0.55
     seismo
    0.55
    ən
    0.54
     Allociné
    0.54
     buying
    0.53
     nervioso
    0.52
    Rewrite
    0.52
     tomorrow
    0.52
    Activations Density 0.153%

    No Known Activations