Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 14922
    Prev
    Next
    INDEX
    Explanations

    words related to personal experiences and sufferings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iverr
    -0.63
     ListTile
    -0.60
     tué
    -0.59
    bootstrapcdn
    -0.55
     sangue
    -0.55
    enswert
    -0.55
     helst
    -0.53
    bitkan
    -0.52
     posando
    -0.52
    AlterField
    -0.52
    POSITIVE LOGITS
     experienced
    3.93
    experienced
    3.52
     experience
    3.45
     Experienced
    3.15
     Experience
    3.08
    experience
    3.06
     experiencing
    3.03
    Experience
    2.98
     EXPERI
    2.95
     experiences
    2.88
    Activations Density 0.108%

    No Known Activations