Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 2969
    Prev
    Next
    INDEX
    Explanations

    references to dietary deficiencies and related public health measures

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

    after "on" and "wings"

    np_acts-logits-general · gemini-2.0-flash

    antenna and attachment

    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
     الحره
    -0.70
     سكانية
    -0.66
    KEYCODE
    -0.66
    Décès
    -0.66
     filtrate
    -0.65
    UnknownFieldSet
    -0.65
     decompression
    -0.62
    SharedCtor
    -0.62
    __((
    -0.59
     Audiodateien
    -0.59
    POSITIVE LOGITS
     antenna
    0.69
     attached
    0.65
     antennas
    0.65
     front
    0.64
    antenna
    0.64
     attachment
    0.60
     Antenna
    0.58
    Antenna
    0.58
     antena
    0.57
     attachments
    0.57
    Activations Density 0.479%

    No Known Activations