© 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. 2-GEMMASCOPE-RES-16K
    11. 1809
    Prev
    Next
    INDEX
    Explanations

    expressions of opinion or sentiment regarding situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ehem
    -0.48
    Maps
    -0.45
     وهي
    -0.45
    سطس
    -0.44
    maps
    -0.44
     accedere
    -0.43
     ladite
    -0.43
    })));
    -0.43
     montagna
    -0.43
     Numerade
    -0.43
    POSITIVE LOGITS
    AndEndTag
    1.04
    IntoConstraints
    0.76
    InjectAttribute
    0.75
    Datuak
    0.73
     становника
    0.71
    CloseOperation
    0.71
    principalTable
    0.68
    mybatisplus
    0.67
    :+:
    0.67
     nakalista
    0.67
    Activations Density 0.247%

    No Known Activations