Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12114
    Prev
    Next
    INDEX
    Explanations

    key-value pairs and their corresponding data structures in coding syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shakspeare
    -1.13
     itſelf
    -1.09
     Reſ
    -1.03
     noastre
    -1.02
     Anſ
    -1.01
     Monfieur
    -1.00
     photolibrary
    -0.99
     Diſ
    -0.99
     îna
    -0.97
     himſelf
    -0.96
    POSITIVE LOGITS
     m
    0.94
     v
    0.93
     y
    0.91
     s
    0.91
     _
    0.89
     p
    0.89
     c
    0.89
     get
    0.87
    — 
    0.86
     id
    0.86
    Activations Density 2.535%

    No Known Activations