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. 2-GEMMASCOPE-RES-16K
    6. 6636
    Prev
    Next
    INDEX
    Explanations

    instances of the word "complaint" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
    tagHelperRunner
    -0.66
     leher
    -0.63
     Dud
    -0.60
     dignidad
    -0.59
    Fer
    -0.58
     scheda
    -0.56
     Huck
    -0.56
    dyti
    -0.54
    IonicModule
    -0.54
     Ter
    -0.53
    POSITIVE LOGITS
     complaint
    2.43
     complaints
    2.43
     complain
    2.34
     Complaints
    2.22
     Complaint
    2.18
     complaining
    2.15
     complains
    2.10
     complained
    2.08
    Complaints
    2.00
    complaint
    1.96
    Activations Density 0.076%

    No Known Activations