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. 21-GEMMASCOPE-RES-16K
    6. 2020
    Prev
    Next
    INDEX
    Explanations

    references to academic research and studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.69
     sobra
    -0.58
     manquer
    -0.56
    +#+#
    -0.54
     commenting
    -0.54
    ⓘ
    -0.53
     sanitaires
    -0.51
     ratification
    -0.51
     resistir
    -0.50
     pourtant
    -0.50
    POSITIVE LOGITS
     teamed
    0.79
    まず
    0.77
     recruited
    0.76
     first
    0.76
     use
    0.76
     aim
    0.75
     partnered
    0.75
     created
    0.72
     hope
    0.72
     divide
    0.71
    Activations Density 0.508%

    No Known Activations