© 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. 16-GEMMASCOPE-RES-16K
    6. 7887
    Prev
    Next
    INDEX
    Explanations

    phrases related to diplomatic initiatives or international relations

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

    Text after Q: or /*

    np_acts-logits-general · gemini-2.0-flash

    code and internationalization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Usual
    -0.65
     usually
    -0.60
     usual
    -0.60
     disambiguazione
    -0.59
    usual
    -0.58
     weirdly
    -0.57
     DAMAGES
    -0.57
     Usual
    -0.57
     dunno
    -0.57
    usually
    -0.57
    POSITIVE LOGITS
     initiatives
    0.85
     reaffirm
    0.71
    SequentialGroup
    0.68
    HasForeignKey
    0.68
     partnerships
    0.64
     Initiatives
    0.64
     soulign
    0.62
     iniciativas
    0.62
    だからこそ
    0.62
     strengthening
    0.61
    Activations Density 0.216%

    No Known Activations