© 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. 7-GEMMASCOPE-RES-16K
    11. 4170
    Prev
    Next
    INDEX
    Explanations

    references to particles and their associated properties or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     storici
    -0.90
    Bew
    -0.86
     contextLoads
    -0.86
    ntgen
    -0.84
    ltä
    -0.82
    rrggbb
    -0.81
    ContextCompat
    -0.77
     tecnici
    -0.76
     thermoc
    -0.75
     Lilian
    -0.75
    POSITIVE LOGITS
     particles
    1.75
     Particles
    1.53
    particles
    1.53
     particle
    1.41
    Particles
    1.40
     Particle
    1.36
    particle
    1.30
    Particle
    1.29
    粒子
    1.08
     particules
    1.05
    Activations Density 0.129%

    No Known Activations