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-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 8042
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to emotional or psychological struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antidesliz
    -0.43
     llavero
    -0.40
     normaux
    -0.36
     personalizado
    -0.36
     colgantes
    -0.35
     lecteurs
    -0.34
     feroit
    -0.34
     administrativo
    -0.34
     beliau
    -0.34
     carattere
    -0.33
    POSITIVE LOGITS
     חיצוניים
    0.70
    endphp
    0.68
    namb
    0.66
     referrerpolicy
    0.66
     percol
    0.65
    ⓧ
    0.65
     nahilalakip
    0.64
    jsonwebtoken
    0.61
    /***/
    0.60
     незавершена
    0.57
    Activations Density 0.648%

    No Known Activations