© 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. 10-GEMMASCOPE-RES-16K
    6. 1890
    Prev
    Next
    INDEX
    Explanations

    references to statistical data and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "):
    
    -1.07
    تقاوى
    -1.05
    sidemargin
    -1.04
    )}</
    -1.02
    Geplaatst
    -1.02
    uxxxx
    -1.02
    "]);
    
    -1.00
    protoimpl
    -0.99
    ########.
    -0.99
    ')):
    -0.99
    POSITIVE LOGITS
    ,
    0.57
    .
    0.54
     courriel
    0.42
    ).
    0.41
     and
    0.40
     iga
    0.38
    。
    0.37
     vagues
    0.36
     esame
    0.36
    readInt
    0.36
    Activations Density 0.478%

    No Known Activations