© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 8463
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific experimentation and measurement stability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstrumentedTest
    -0.63
     متعلقه
    -0.63
    
    -0.56
    jsdelivr
    -0.52
    ximately
    -0.50
     AssemblyCompany
    -0.49
    期刊论文
    -0.49
    expandindo
    -0.49
     kasarigan
    -0.46
    évaluateur
    -0.45
    POSITIVE LOGITS
     state
    3.98
    state
    3.65
     State
    3.25
    State
    3.16
     STATE
    3.11
    STATE
    2.94
     estado
    2.57
     states
    2.54
    states
    2.27
     état
    2.20
    Activations Density 0.822%

    No Known Activations