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. 4-GEMMASCOPE-RES-16K
    6. 10944
    Prev
    Next
    INDEX
    Explanations

    cryptographic key and algorithm specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.84
    SpringBootTest
    -0.82
    richTextPanel
    -0.79
    interopRequire
    -0.79
     snippetHide
    -0.74
     NSCoder
    -0.74
    jooq
    -0.71
    hésite
    -0.71
    henswürdigkeiten
    -0.71
    IsContent
    -0.70
    POSITIVE LOGITS
    Tr
    0.51
    +#+
    0.51
    tek
    0.50
    mut
    0.49
    es
    0.48
    lek
    0.47
    ResumeLayout
    0.47
    الإنجليزية
    0.47
     ples
    0.47
    ssil
    0.46
    Activations Density 0.082%

    No Known Activations