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. 22-GEMMASCOPE-RES-16K
    6. 13827
    Prev
    Next
    INDEX
    Explanations

    positive descriptions related to job opportunities and benefits

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

    benefits, salary, or job perks

    np_acts-logits-general · gemini-2.0-flash

    job benefits culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    testens
    -0.62
     TextInputType
    -0.56
    gitto
    -0.51
     >=",
    -0.51
    HandlerContext
    -0.49
    OOTDTY
    -0.49
    WebControls
    -0.48
    }$​
    -0.47
     gynhyrchwyd
    -0.47
    glises
    -0.47
    POSITIVE LOGITS
     culture
    0.99
     perks
    0.92
     flexible
    0.87
     benefits
    0.87
     flexibility
    0.83
    Culture
    0.78
     opportunities
    0.78
     camaraderie
    0.77
     Culture
    0.77
     Flexible
    0.76
    Activations Density 0.117%

    No Known Activations