© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 4355
    Prev
    Next
    INDEX
    Explanations

    phrases related to research methodology and data collection processes

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

    "interviews" or "research"

    np_acts-logits-general · gemini-2.0-flash

    conducting interviews

    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
    كذا
    -0.51
     Polda
    -0.47
    mapStateToProps
    -0.47
     fidèles
    -0.46
    jsdelivr
    -0.45
     Schlu
    -0.44
     kvä
    -0.44
     comemor
    -0.43
    Ooooo
    -0.43
    ROIT
    -0.43
    POSITIVE LOGITS
     interviews
    2.29
     interviewing
    2.10
     interview
    2.08
     interviewed
    2.03
     Interviews
    1.98
    Interviews
    1.90
    interview
    1.83
     Interview
    1.82
    Interview
    1.75
     interviewees
    1.72
    Activations Density 0.404%

    No Known Activations