© 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. 21-GEMMASCOPE-RES-16K
    6. 13369
    Prev
    Next
    INDEX
    Explanations

    expressions of public sentiment and social engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]}>
    -0.63
     Référence
    -0.53
     själv
    -0.53
    LikeLike
    -0.52
     Públicas
    -0.51
     sozinho
    -0.51
    Capítulo
    -0.51
    AnchorStyles
    -0.50
    Kanpo
    -0.49
    Viitteet
    -0.49
    POSITIVE LOGITS
     flock
    1.19
     flocked
    1.13
     clamor
    0.97
     Flock
    0.90
     themselves
    0.89
    flock
    0.83
     clamour
    0.82
    themselves
    0.79
     voting
    0.79
    纷纷
    0.78
    Activations Density 0.633%

    No Known Activations