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. 3764
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to cache and memory architecture

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

    XML or code parameters

    np_acts-logits-general · gemini-2.0-flash

    cache, memory, bank, ports

    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
     invokingState
    -0.62
     unknownFields
    -0.61
     owe
    -0.53
    脚注の使い方
    -0.51
    SNMP
    -0.51
    Wikis
    -0.47
     Koss
    -0.46
     fitting
    -0.46
    CppMethod
    -0.45
    FTFY
    -0.45
    POSITIVE LOGITS
    roek
    0.58
    rrggbb
    0.56
    DateTimeField
    0.54
    bram
    0.53
    bindParam
    0.53
     Стар
    0.52
     souris
    0.52
    Ranks
    0.52
     bram
    0.51
    NameInMap
    0.51
    Activations Density 0.806%

    No Known Activations