© 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. 15660
    Prev
    Next
    INDEX
    Explanations

    phrases and questions related to the concept of "how" in various contexts

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

    Comes after "how"

    np_acts-logits-general · gemini-2.0-flash

    how followed by explanations

    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
     massimo
    -0.51
    </td>
    -0.48
    azi
    -0.44
     alasan
    -0.44
     رفتن
    -0.43
    weta
    -0.42
     σχέ
    -0.42
     görü
    -0.42
    wis
    -0.42
    正在
    -0.42
    POSITIVE LOGITS
     incredibly
    0.87
     ProtoMessage
    0.78
     great
    0.77
    expandindo
    0.76
     incredible
    0.76
     unbelievably
    0.74
     Combien
    0.73
     wonderful
    0.73
    @[+][
    0.73
    RectangleBorder
    0.72
    Activations Density 0.060%

    No Known Activations