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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6409
    Prev
    Next
    INDEX
    Explanations

    features related to enhanced multimedia experiences in technology products

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

    phrases related to enjoyment, experience, and sensory pleasure.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @danielepoterti
    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
    ">@
    -0.65
     Nacionales
    -0.60
     noqa
    -0.60
    NameInMap
    -0.59
    =&
    -0.56
    ⓘ
    -0.56
     intptr
    -0.56
    一応
    -0.56
    TProtocol
    -0.56
     principally
    -0.55
    POSITIVE LOGITS
    حياته
    0.60
    openhague
    0.55
     لذت
    0.52
     المتحدة
    0.51
     descomp
    0.51
    bbled
    0.50
     ddelweddau
    0.48
    ruly
    0.47
     passphrase
    0.46
    araoh
    0.46
    Activations Density 0.304%

    No Known Activations