© 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. 663
    Prev
    Next
    INDEX
    Explanations

    countable quantities related to populations or groups

    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
    ModelSerializer
    -0.42
    󠁴
    -0.40
     }{@
    -0.34
    Ƚ
    -0.33
     تكبرها
    -0.33
    ronpa
    -0.33
    setViewportView
    -0.31
    __()
    -0.30
     flach
    -0.28
    illermo
    -0.28
    POSITIVE LOGITS
     millions
    3.23
     thousands
    3.05
    millions
    2.80
    thousands
    2.70
     Millions
    2.70
     Thousands
    2.64
    Millions
    2.61
    Thousands
    2.61
     billions
    2.55
     hundreds
    2.48
    Activations Density 0.712%

    No Known Activations