© 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. 8982
    Prev
    Next
    INDEX
    Explanations

    references to the listener or reader, particularly in the form of questions about their beliefs or experiences

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

    "you" followed by a verb relating to thought

    np_acts-logits-general · gemini-2.0-flash

    questions about what you know

    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
    Хьажоргаш
    -0.81
     parteci
    -0.64
    >>>>>>>
    -0.55
    قایناقلار
    -0.53
    convite
    -0.52
     חיצוניים
    -0.52
    NavController
    -0.51
     relâche
    -0.51
     angekommen
    -0.48
    EndContext
    -0.48
    POSITIVE LOGITS
    UserScript
    0.66
    terase
    0.63
     QName
    0.62
    Ikr
    0.53
     ?$
    0.53
     SEDS
    0.52
    ENSA
    0.51
     alia
    0.50
    .*")]
    0.50
    zü
    0.50
    Activations Density 0.082%

    No Known Activations