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. 15869
    Prev
    Next
    INDEX
    Explanations

    terms related to different categories and classifications

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

    starting with "Sub"

    np_acts-logits-general · gemini-2.0-flash

    words starting with sub-

    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
     ?>>
    -0.64
    ̀ng
    -0.60
    mstyle
    -0.59
    APIView
    -0.58
     Asher
    -0.55
     }}"></
    -0.54
     ?>">
    -0.54
    migrationBuilder
    -0.54
     Spi
    -0.54
    pulumi
    -0.54
    POSITIVE LOGITS
    SUB
    1.27
     SUB
    1.26
     Sub
    1.23
     getSub
    1.18
     sub
    1.15
    Sub
    1.13
     subs
    1.09
    sub
    1.01
    Subs
    0.98
     Subs
    0.98
    Activations Density 0.229%

    No Known Activations