© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11424
    Prev
    Next
    INDEX
    Explanations

    statements related to purpose, objectives, and intentions in written content

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

    followed by "purpose," "aim," "goal," or "objective."

    np_acts-logits-general · gemini-2.0-flash

    statement of purpose or goal

    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
    uxxxx
    -0.69
    +#+#
    -0.68
    mybatisplus
    -0.65
     AssemblyCompany
    -0.65
    rungsseite
    -0.63
    SPATH
    -0.58
     Blockly
    -0.58
    GEBURTSDATUM
    -0.57
     BrowserModule
    -0.57
    HostException
    -0.56
    POSITIVE LOGITS
     aim
    2.73
     purpose
    2.67
     goal
    2.65
     objective
    2.30
    goal
    2.16
     Purpose
    2.14
     objetivo
    2.11
    Purpose
    2.07
    purpose
    2.06
     tujuan
    2.01
    Activations Density 0.637%

    No Known Activations