© 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. 15-GEMMASCOPE-RES-16K
    6. 4869
    Prev
    Next
    INDEX
    Explanations

    terms related to data management and processing efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.92
     Monfieur
    -0.87
     myſelf
    -0.81
     ་་
    -0.81
     itſelf
    -0.81
     poffible
    -0.81
     chofe
    -0.81
     Италијани
    -0.81
    ſelves
    -0.80
     ―――――
    -0.80
    POSITIVE LOGITS
     or
    0.70
     mode
    0.59
     se
    0.58
    imageshack
    0.57
     versus
    0.57
     vs
    0.56
    <eos>
    0.54
     type
    0.53
     kind
    0.51
     الدولى
    0.48
    Activations Density 0.476%

    No Known Activations