© 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. 3-GEMMASCOPE-RES-16K
    11. 8527
    Prev
    Next
    INDEX
    Explanations

    the future tense of the verb "to be."

    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
     purpoſe
    -0.99
    OGND
    -0.93
     Jefus
    -0.92
     itſelf
    -0.91
     pleaſure
    -0.87
     صوتيه
    -0.86
    AsUp
    -0.84
    存于互联网档案馆
    -0.84
     ſtate
    -0.83
     ſche
    -0.83
    POSITIVE LOGITS
     youll
    0.66
     You
    0.65
     您
    0.54
     będziesz
    0.53
     получите
    0.52
     verá
    0.51
     I
    0.50
     seen
    0.50
     you
    0.50
    You
    0.49
    Activations Density 0.112%

    No Known Activations