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. 14-GEMMASCOPE-RES-16K
    6. 4166
    Prev
    Next
    INDEX
    Explanations

    terms related to family planning and reproductive choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.98
    شهاد
    -0.70
     ModelExpression
    -0.66
     Falta
    -0.64
    teht
    -0.63
     ويكيپيديا
    -0.63
     resourceCulture
    -0.61
    ConstraintMaker
    -0.56
     shur
    -0.56
    dropna
    -0.55
    POSITIVE LOGITS
     unwanted
    1.20
     unwelcome
    0.71
    undes
    0.60
     undesirable
    0.60
     ناخ
    0.59
     unsolicited
    0.58
     undes
    0.56
     uncontrollable
    0.51
     intrusive
    0.50
     un
    0.50
    Activations Density 0.498%

    No Known Activations