Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 6780
    Prev
    Next
    INDEX
    Explanations

    references to situations or actions that take place behind the scenes or in secret

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invitamos
    -0.70
    سو
    -0.68
     Stockton
    -0.65
     davis
    -0.61
     Davis
    -0.61
    чие
    -0.59
     Landis
    -0.59
    präche
    -0.59
     Chat
    -0.58
     Fluss
    -0.58
    POSITIVE LOGITS
     Behind
    1.59
     behind
    1.55
    Behind
    1.53
     BEHIND
    1.48
    behind
    1.39
    HIND
    1.21
     derrière
    1.15
    Hinter
    1.11
     Hinter
    1.08
     dietro
    0.98
    Activations Density 0.041%

    No Known Activations