© 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. 9908
    Prev
    Next
    INDEX
    Explanations

    instances of the word "weak" in various contexts

    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
    MLLoader
    -0.64
    :✨
    -0.63
    AndEndTag
    -0.61
    Grath
    -0.60
    TagHelper
    -0.59
     pl
    -0.58
    ↵
    -0.57
    SerializedSize
    -0.57
     μαζί
    -0.57
    ServletException
    -0.55
    POSITIVE LOGITS
     weak
    3.14
     Weak
    3.10
    weak
    2.95
    Weak
    2.83
     weakness
    2.42
     weaker
    2.35
     weakly
    2.20
     weakest
    2.17
     Weakness
    2.16
    WEAK
    2.15
    Activations Density 0.087%

    No Known Activations