© 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. 2-GEMMASCOPE-RES-16K
    6. 13384
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison or similarity

    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
    ſelf
    -0.88
     pleaſure
    -0.83
     houſe
    -0.82
     purpoſe
    -0.81
     ſol
    -0.81
     myſelf
    -0.79
    ſelves
    -0.79
     ſche
    -0.78
     ſtate
    -0.77
     itſelf
    -0.77
    POSITIVE LOGITS
     as
    2.14
     sebagai
    1.21
     ως
    1.05
    作为
    0.99
    sebagai
    0.97
     Sebagai
    0.91
    Sebagai
    0.88
    作為
    0.88
     jako
    0.87
     As
    0.84
    Activations Density 0.273%

    No Known Activations