© 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. 8102
    Prev
    Next
    INDEX
    Explanations

    terms related to circular structures and concepts

    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
     للمعارف
    -0.62
    ########.
    -0.57
     calloc
    -0.57
    taobao
    -0.56
    +};
    -0.55
     sauvage
    -0.55
    antaranya
    -0.54
    BeNil
    -0.53
    SAE
    -0.53
     overras
    -0.51
    POSITIVE LOGITS
     loops
    0.76
     CIR
    0.74
     Loops
    0.68
    NewUrlParser
    0.67
    jerk
    0.67
     breaker
    0.66
    Circles
    0.65
    loop
    0.65
     circles
    0.65
    loops
    0.65
    Activations Density 0.210%

    No Known Activations