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. 18-GEMMASCOPE-RES-16K
    6. 3974
    Prev
    Next
    INDEX
    Explanations

    phrases related to leadership and management in healthcare settings

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

    Statistical study descriptions

    np_acts-logits-general · gemini-2.0-flash

    academic research and surveys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Havolalar
    -0.59
     IANS
    -0.56
     milhões
    -0.55
    choly
    -0.53
    ABAD
    -0.52
     WASHINGTON
    -0.52
     récemment
    -0.52
    StateException
    -0.52
    xnn
    -0.51
     dnes
    -0.51
    POSITIVE LOGITS
    GOTREF
    0.74
     researcher
    0.71
     respondents
    0.67
     qualitative
    0.63
     questionnaires
    0.63
    AndEndTag
    0.62
     Interview
    0.60
     research
    0.60
     survey
    0.60
     interviews
    0.60
    Activations Density 0.575%

    No Known Activations