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. 16-GEMMASCOPE-RES-16K
    6. 1604
    Prev
    Next
    INDEX
    Explanations

    phrases related to collective actions or attempts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "should," "to," "of," or "has"

    np_acts-logits-general · gemini-2.0-flash

    making efforts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     privileges
    -0.70
    privile
    -0.67
    kespea
    -0.65
     Steen
    -0.65
     Tans
    -0.65
     DeL
    -0.64
     PSM
    -0.63
     يتيمه
    -0.63
     Balt
    -0.63
    ekw
    -0.61
    POSITIVE LOGITS
     efforts
    1.62
     Efforts
    1.60
     effort
    1.59
     Effort
    1.47
    Effort
    1.30
    efforts
    1.27
     EFF
    1.21
    effort
    1.16
     esfuerzo
    1.05
     attempts
    1.03
    Activations Density 0.079%

    No Known Activations