© 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. 1178
    Prev
    Next
    INDEX
    Explanations

    patterns related to frequency and quantity in various contexts

    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
     disambiguazione
    -0.60
    UrlResolution
    -0.59
    expandindo
    -0.58
     Normdatei
    -0.54
    ValueGenerated
    -0.51
    ResumeLayout
    -0.50
    fortawesome
    -0.50
    Enllaces
    -0.49
    zenio
    -0.49
     jLabel
    -0.48
    POSITIVE LOGITS
     per
    1.52
     a
    0.90
    ต่อ
    0.85
     every
    0.76
     annually
    0.76
    per
    0.76
     sehari
    0.73
     PER
    0.73
     प्रति
    0.71
     daily
    0.71
    Activations Density 0.275%

    No Known Activations