© 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. 514
    Prev
    Next
    INDEX
    Explanations

    phrases related to partnership and collaboration

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

    "of" followed by a determiner

    np_acts-logits-general · gemini-2.0-flash

    of the

    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
     Cæsar
    -0.70
     Shakspeare
    -0.62
     înainte
    -0.61
     invitamos
    -0.60
     Atiku
    -0.58
     Shaksp
    -0.56
     garmin
    -0.55
     Oedipus
    -0.55
     Avignon
    -0.54
     împreună
    -0.53
    POSITIVE LOGITS
     the
    1.40
     their
    1.01
     a
    0.97
     an
    0.96
     sorts
    0.95
    .)}
    0.93
    .}(
    0.92
     its
    0.91
     those
    0.89
     our
    0.89
    Activations Density 1.449%

    No Known Activations