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. 15-GEMMASCOPE-RES-16K
    6. 5039
    Prev
    Next
    INDEX
    Explanations

    instances where the subject applies for or discusses job opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Xna
    -0.46
     التش
    -0.45
    vádz
    -0.43
    écuter
    -0.43
    livery
    -0.41
     Dogg
    -0.41
     Precinct
    -0.41
    buz
    -0.41
    koin
    -0.40
    )}_
    -0.40
    POSITIVE LOGITS
     applicants
    0.96
     applicant
    0.94
     Applicant
    0.88
     Candidate
    0.87
     interview
    0.86
     candidate
    0.86
     candidates
    0.85
     candidacy
    0.85
     Applicants
    0.84
     candidats
    0.82
    Activations Density 0.243%

    No Known Activations