© 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. 14-GEMMASCOPE-RES-16K
    11. 4442
    Prev
    Next
    INDEX
    Explanations

    references to actions and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marconi
    -0.76
     Einer
    -0.75
    erequisite
    -0.74
    তথ্যসূত্র
    -0.74
     Latimer
    -0.71
     unsatisfactory
    -0.71
    Soma
    -0.70
     gera
    -0.70
     الخم
    -0.69
     frontiers
    -0.69
    POSITIVE LOGITS
     ACT
    1.51
     act
    1.49
     acts
    1.46
     Acts
    1.41
     Act
    1.39
    Act
    1.17
     acted
    1.16
     Acton
    1.16
    Acts
    1.16
    ACT
    1.16
    Activations Density 0.072%

    No Known Activations