© 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 EvalsExportsAPI 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. 15031
    Prev
    Next
    INDEX
    Explanations

    terms related to "monocyte" and "monotonous" attributes in various contexts

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

    starting with "Mon" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    words starting with Mon

    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
    ########.
    -0.70
    ValueStyle
    -0.67
    mybatisplus
    -0.58
    Parcelize
    -0.58
    RESULTS
    -0.56
     CreateTagHelper
    -0.55
     calendriers
    -0.55
    Autores
    -0.54
     RESULTS
    -0.53
    CppMethod
    -0.53
    POSITIVE LOGITS
     MON
    1.17
     Mon
    1.11
    MON
    1.02
    Mon
    1.01
    mon
    0.88
    gomery
    0.85
     Monro
    0.85
     mons
    0.83
     Monitors
    0.80
    IMON
    0.79
    Activations Density 0.108%

    No Known Activations