© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11021
    Prev
    Next
    INDEX
    Explanations

    references to mental health resources and support

    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
     mendukung
    -0.45
    stdc
    -0.43
    :✨
    -0.43
    InputBorder
    -0.43
    vician
    -0.40
    presse
    -0.40
    pense
    -0.39
    见证
    -0.39
    horabuena
    -0.39
     inspec
    -0.39
    POSITIVE LOGITS
     seek
    1.60
     seeking
    1.59
    Seeking
    1.40
     Seeking
    1.40
     Seek
    1.39
    seek
    1.37
    seeking
    1.35
    Seek
    1.34
     sought
    1.33
     seeks
    1.33
    Activations Density 0.515%

    No Known Activations