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. 1436
    Prev
    Next
    INDEX
    Explanations

    words related to sending something or the act of transmission

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

    sending something

    np_acts-logits-general · gemini-2.0-flash

    sending or sent

    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
    MigrationBuilder
    -0.66
     Normdatei
    -0.65
    UrlResolution
    -0.64
    millimeters
    -0.62
    cination
    -0.61
    ButterKnife
    -0.60
    TagMode
    -0.59
    XmlAccessType
    -0.58
     Roskov
    -0.57
    帖最后由
    -0.57
    POSITIVE LOGITS
     Sends
    1.24
     sends
    1.18
     SEND
    1.13
     send
    1.12
     sent
    1.08
     Send
    1.02
     SENT
    1.02
    SEND
    1.00
     sending
    1.00
     Sending
    0.98
    Activations Density 0.104%

    No Known Activations