© 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. 13290
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and economic issues

    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
    ajiban
    -0.58
    fml
    -0.57
    Tracce
    -0.53
    unicaciones
    -0.51
    apunov
    -0.49
    "><?
    -0.48
    Gemeinden
    -0.47
    sscanf
    -0.47
    illoma
    -0.45
    PerformLayout
    -0.45
    POSITIVE LOGITS
     their
    4.11
    Their
    3.69
    their
    3.61
     Their
    3.46
     they
    3.17
     THEIR
    2.94
     themselves
    2.85
     leur
    2.85
    他们的
    2.83
     loro
    2.81
    Activations Density 5.940%

    No Known Activations