© 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. 17-GEMMASCOPE-RES-16K
    6. 9454
    Prev
    Next
    INDEX
    Explanations

    the term "subject" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bianche
    -0.57
     fidelity
    -0.54
     propter
    -0.54
     Readiness
    -0.52
     Timberlake
    -0.51
    íticos
    -0.50
     poplar
    -0.50
    раздо
    -0.49
     Antiquity
    -0.47
     cistern
    -0.47
    POSITIVE LOGITS
     matter
    1.96
    matter
    1.70
     Matter
    1.56
    Matter
    1.51
     MATTER
    1.50
     subject
    1.20
     Subject
    1.16
     subjects
    1.13
    setSubject
    1.12
    SUBJECT
    1.11
    Activations Density 0.151%

    No Known Activations