© 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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8236
    Prev
    Next
    INDEX
    Explanations

    references to thresholds in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 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
     ―――――
    -1.04
     Efq
    -1.04
     Monfieur
    -1.02
     ſever
    -1.01
     ſtate
    -1.01
     purpoſe
    -1.00
     myſelf
    -0.99
     Jefus
    -0.98
     pleaſure
    -0.98
     Diſ
    -0.98
    POSITIVE LOGITS
     A
    0.75
     no
    0.73
     se
    0.72
     X
    0.71
     brief
    0.69
     
    0.69
     L
    0.69
     Se
    0.68
     n
    0.66
     V
    0.66
    Activations Density 0.161%

    No Known Activations