© 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. 4032
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or limitations

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

    "but not limited to" phrase

    np_acts-logits-general · gemini-2.0-flash

    but not limited to

    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
     least
    -0.85
    Least
    -0.68
     Least
    -0.65
    least
    -0.63
     leaſt
    -0.62
     Efq
    -0.62
    tdessen
    -0.57
    uestamente
    -0.56
     LEAST
    -0.56
    tvguidetime
    -0.53
    POSITIVE LOGITS
    HasAnnotation
    0.58
    нциклопедия
    0.54
    EndProject
    0.53
    PropertyChanging
    0.51
     FixedUpdate
    0.51
    Autoritní
    0.49
     scă
    0.48
    CodeAttribute
    0.47
     unknownFields
    0.47
     fija
    0.47
    Activations Density 0.081%

    No Known Activations