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. 4-GEMMASCOPE-RES-16K
    6. 11068
    Prev
    Next
    INDEX
    Explanations

    terms related to messaging and command interactions within a system, particularly associated with Slack and API functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.61
    EndProject
    -0.60
    Życiorys
    -0.60
    heça
    -0.57
    UIControlState
    -0.53
     CHtml
    -0.53
    NOPQRST
    -0.52
    ⓘ
    -0.51
    apimachinery
    -0.49
     súng
    -0.48
    POSITIVE LOGITS
    jda
    0.65
    discord
    0.63
    bukkit
    0.59
    gameserver
    0.59
    ']],
    0.59
    تفصیلات
    0.57
     Discord
    0.57
     fevere
    0.55
    채
    0.55
     dischar
    0.55
    Activations Density 0.244%

    No Known Activations