© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3956
    Prev
    Next
    INDEX
    Explanations

    instances of the word "act" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.54
     InputDecoration
    -0.47
     Lur
    -0.41
    izon
    -0.40
     Nirvana
    -0.40
    omethyl
    -0.38
    招待
    -0.38
    lero
    -0.38
    resher
    -0.38
    zun
    -0.38
    POSITIVE LOGITS
     act
    4.13
    act
    3.69
     Act
    3.63
    Act
    3.53
     acts
    3.06
     ACT
    2.83
    ACT
    2.72
     Acts
    2.67
     acted
    2.67
    acts
    2.66
    Activations Density 0.144%

    No Known Activations