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. 24-GEMMASCOPE-RES-16K
    6. 8039
    Prev
    Next
    INDEX
    Explanations

    phrases related to recognition and achievements in the context of leadership and innovation

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

    following "hire" or "hired"

    np_acts-logits-general · gemini-2.0-flash

    hiring and recruitment actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScaleMode
    -0.83
     BoxFit
    -0.70
    WithIOException
    -0.67
    verwijspagina
    -0.64
     المعيارى
    -0.62
     فريبيس
    -0.59
    EndInit
    -0.59
     المعرف
    -0.56
    MemoryWarning
    -0.52
    Disconnected
    -0.52
    POSITIVE LOGITS
     hiring
    1.51
     hire
    1.47
     hired
    1.39
     hires
    1.36
     Hire
    1.26
     recruited
    1.25
    Hire
    1.24
     appoint
    1.22
     recruit
    1.21
     Hiring
    1.19
    Activations Density 0.345%

    No Known Activations