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. 10948
    Prev
    Next
    INDEX
    Explanations

    specific medical and biological terminology, particularly related to treatment and conditions

    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
     StringTokenizer
    -0.58
    igny
    -0.55
    JsonHelper
    -0.52
    utia
    -0.52
    ثل
    -0.49
     IMPLIED
    -0.48
    むしろ
    -0.48
    ิ่ง
    -0.46
     preparation
    -0.46
     Affiliations
    -0.45
    POSITIVE LOGITS
    migrationBuilder
    0.91
     gyhoeddwyd
    0.87
     nahilalakip
    0.82
    rungsseite
    0.81
    Portale
    0.77
    fjspx
    0.74
    ResumeLayout
    0.73
     resourceCulture
    0.73
     ویکی‌پدی
    0.71
    kuuta
    0.70
    Activations Density 2.275%

    No Known Activations