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. 3-GEMMASCOPE-RES-16K
    6. 12894
    Prev
    Next
    INDEX
    Explanations

    the presence of forms of the verb "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.58
     Suara
    -0.57
     ProtoMessage
    -0.56
    RegistryLite
    -0.56
     ISNI
    -0.55
    ::_('
    -0.54
    Népesség
    -0.54
    MemoryWarning
    -0.54
     ""],
    -0.54
    plat
    -0.54
    POSITIVE LOGITS
    脚注の使い方
    0.74
    wurde
    0.63
    LEncoder
    0.62
    ನ್ನು
    0.61
     للمعارف
    0.60
    被他
    0.59
     został
    0.58
     zostały
    0.58
     be
    0.56
    protoimpl
    0.56
    Activations Density 0.791%

    No Known Activations