© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 3122
    Prev
    Next
    INDEX
    Explanations

    emotional descriptors and adjectives related to positive and negative sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.78
    UpInside
    -0.78
    providedIn
    -0.65
     MonoBehaviour
    -0.61
    hyrchwyd
    -0.60
     обла
    -0.60
    tvguidetime
    -0.57
    glGen
    -0.56
    )|^{
    -0.56
    colazione
    -0.56
    POSITIVE LOGITS
     shocking
    0.75
     gratifying
    0.71
     itſelf
    0.69
     upsetting
    0.68
     distressing
    0.67
     frustrating
    0.67
     horrifying
    0.66
    astrous
    0.66
     dangerous
    0.66
     humiliating
    0.65
    Activations Density 0.226%

    No Known Activations