© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3381
    Prev
    Next
    INDEX
    Explanations

    instructions related to setting up and managing workspaces in a software context

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

    Follows a comma or "we"

    np_acts-logits-general · gemini-2.0-flash

    we do now

    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
    GEBURTSDATUM
    -0.62
    principalColumn
    -0.55
     BytesLike
    -0.53
    ご了承ください
    -0.53
    таратура
    -0.52
     zewnętrzne
    -0.51
    ')),
    -0.51
     disambiguazione
    -0.50
    ::*;
    -0.49
    IONE
    -0.49
    POSITIVE LOGITS
     now
    2.74
    now
    2.22
    Now
    2.18
     Now
    2.13
     maintenant
    2.08
     теперь
    2.07
    Теперь
    2.02
     ahora
    1.98
     Теперь
    1.97
     agora
    1.83
    Activations Density 0.847%

    No Known Activations