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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9568
    Prev
    Next
    INDEX
    Explanations

    phrases related to work experience and qualifications

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

    professional or military experience

    np_acts-logits-general · gemini-2.0-flash

    quantifying experience

    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
    textTheme
    -0.60
     صوتيه
    -0.54
    BindView
    -0.53
    nloa
    -0.49
     ويكيپيديا
    -0.48
    OGND
    -0.48
    createCell
    -0.47
    Indice
    -0.47
    ocera
    -0.46
    brium
    -0.46
    POSITIVE LOGITS
     experience
    2.51
    experience
    2.19
     Experience
    2.10
    Experience
    2.07
     EXPERIENCE
    2.00
     expérience
    1.96
     experiences
    1.92
     experiencia
    1.82
    EXPERIENCE
    1.77
     experiência
    1.76
    Activations Density 0.181%

    No Known Activations