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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14578
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to software development and programming

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    used for creation or based on

    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
    AnimationsModule
    -0.79
    enumi
    -0.71
    ActionCreators
    -0.67
    HostException
    -0.66
    addCriterion
    -0.65
     оригіналу
    -0.64
    CloseOperation
    -0.62
    ;->
    -0.61
    CppCodeGen
    -0.60
    ServletException
    -0.60
    POSITIVE LOGITS
     using
    0.86
     åt
    0.79
     for
    0.74
     based
    0.70
     usable
    0.69
    用于
    0.68
    ึ้น
    0.64
     USING
    0.63
     suitable
    0.63
     используя
    0.61
    Activations Density 0.784%

    No Known Activations