© 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. 2-GEMMASCOPE-RES-16K
    11. 8805
    Prev
    Next
    INDEX
    Explanations

    references to towers and related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obě
    -0.49
    Sklici
    -0.49
    OGND
    -0.47
    ParallelGroup
    -0.46
    httphttps
    -0.46
    ducted
    -0.45
    essence
    -0.44
    AutoSize
    -0.44
    .*")]
    -0.43
    dchen
    -0.43
    POSITIVE LOGITS
     towers
    0.82
     tower
    0.80
     Tower
    0.77
    Tower
    0.73
    Fav
    0.72
     Fav
    0.71
     Towers
    0.71
    tower
    0.68
    towers
    0.66
     fav
    0.66
    Activations Density 0.086%

    No Known Activations