© 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. 0-GEMMASCOPE-RES-16K
    11. 7564
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ywna
    -0.46
    Xna
    -0.44
     neumáticos
    -0.43
     JG
    -0.43
     JC
    -0.42
     Jerusalén
    -0.42
     RestTemplate
    -0.40
    ::_('
    -0.40
     JK
    -0.40
    ſelves
    -0.40
    POSITIVE LOGITS
     Aj
    1.56
    aj
    1.52
    Aj
    1.48
    uj
    1.38
     aj
    1.36
    taj
    1.33
    ij
    1.31
     Bj
    1.30
    bj
    1.30
    Bj
    1.27
    Activations Density 1.654%

    No Known Activations