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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 14686
    Prev
    Next
    INDEX
    Explanations

    sentences or statements emphasizing or summarizing key points or conclusions

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

    Follows quotation marks or colons

    np_acts-logits-general · gemini-2.0-flash

    quotation marks precede names

    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
     Efq
    -1.17
    StoryboardSegue
    -1.13
    GEBURTSDATUM
    -1.10
     Majefty
    -1.03
     Wikimedijinoj
    -1.03
    +#+#
    -1.03
    RenderAtEndOf
    -1.02
    LookAnd
    -1.01
    DockStyle
    -1.01
    TestingModule
    -1.01
    POSITIVE LOGITS
     “
    1.28
     "
    1.14
    “
    1.10
     “[
    1.00
    “[
    0.96
     «
    0.95
    「
    0.88
    According
    0.83
     "[
    0.81
    Says
    0.80
    Activations Density 0.157%

    No Known Activations