© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4231
    Prev
    Next
    INDEX
    Explanations

    assertive or declarative statements involving emotional or significant events

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

    Sentences ending with names or pronouns

    np_acts-logits-general · gemini-2.0-flash

    both people, other parties

    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
     calendriers
    -0.74
    IntoConstraints
    -0.68
    MENAFN
    -0.57
     AssemblyCompany
    -0.55
    Các
    -0.53
    principalTable
    -0.52
    Cordialement
    -0.51
    simum
    -0.50
    enment
    -0.50
    órum
    -0.49
    POSITIVE LOGITS
     Ambos
    0.81
    Both
    0.74
     Both
    0.72
     him
    0.66
    お互
    0.64
     entrambi
    0.61
    后者
    0.60
     beide
    0.60
     Beide
    0.59
     keduanya
    0.59
    Activations Density 0.596%

    No Known Activations