© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11589
    Prev
    Next
    INDEX
    Explanations

    terms related to digital advertising strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leider
    -0.52
    :][
    -0.52
    PreferredItem
    -0.49
     offenbar
    -0.49
    SequentialGroup
    -0.48
    才會
    -0.48
    webElementXpaths
    -0.48
    setVerticalGroup
    -0.47
    EndContext
    -0.47
     endif
    -0.46
    POSITIVE LOGITS
     unlike
    1.16
    unlike
    1.15
    Unlike
    1.05
     Unlike
    1.04
    不像
    0.77
     compared
    0.71
    Compared
    0.71
     Compared
    0.71
    compared
    0.70
    Plus
    0.68
    Activations Density 0.374%

    No Known Activations