© 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. 7-GEMMASCOPE-RES-16K
    11. 11560
    Prev
    Next
    INDEX
    Explanations

    comparative and evaluative language that indicates relative qualities or degrees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     urbana
    -0.56
     majeur
    -0.55
     diejenigen
    -0.54
     demais
    -0.54
     morales
    -0.53
     totales
    -0.53
     lehetős
    -0.53
     raio
    -0.53
     amines
    -0.52
    inė
    -0.52
    POSITIVE LOGITS
    neté
    0.79
     Мексичка
    0.71
     Paglinawan
    0.71
     ostavi
    0.69
     very
    0.67
    ingly
    0.67
     πιο
    0.66
    "):
    0.63
    },{
    0.63
    IndentedString
    0.62
    Activations Density 0.403%

    No Known Activations