© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 648
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to resource links and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cappuccio
    -0.85
    #+#
    -0.80
     Theſe
    -0.75
    JspWriter
    -0.73
    omiast
    -0.70
    JNIEnv
    -0.70
     мәкал
    -0.68
     sonho
    -0.68
    PMailer
    -0.68
     itſelf
    -0.66
    POSITIVE LOGITS
     rel
    2.95
    rel
    1.71
     Rel
    1.63
    Rel
    1.48
    REL
    1.19
     REL
    1.17
     relati
    1.05
     relish
    0.89
    rela
    0.84
     Rela
    0.82
    Activations Density 0.094%

    No Known Activations