© 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. 17-GEMMASCOPE-RES-16K
    11. 5446
    Prev
    Next
    INDEX
    Explanations

    variations of the prefix "sn" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JULY
    -0.67
    ])):
    -0.66
    richtet
    -0.64
    "]));
    -0.64
    '])){
    -0.62
    Berikut
    -0.60
    mployment
    -0.60
    ]));
    -0.60
    tesi
    -0.60
    ]));
    -0.59
    POSITIVE LOGITS
     Sna
    1.12
    Sna
    1.02
    sna
    0.97
     sna
    0.95
     sn
    0.94
     SNAP
    0.93
     Sn
    0.90
    sn
    0.89
     SN
    0.87
    Snoo
    0.86
    Activations Density 0.137%

    No Known Activations