© 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. 3-GEMMASCOPE-RES-16K
    6. 12140
    Prev
    Next
    INDEX
    Explanations

    sequences of specific symbols or characters, particularly related to formatting or encoding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alſo
    -0.75
     propOrder
    -0.74
     تكبرها
    -0.72
    awtextra
    -0.71
     Theſe
    -0.71
    ])).
    -0.70
    ))).
    -0.69
     Antara
    -0.68
    pilar
    -0.68
     InputDecoration
    -0.67
    POSITIVE LOGITS
    u
    0.58
    尔
    0.53
    im
    0.50
    ri
    0.50
    ir
    0.49
    ْ
    0.49
    ะ
    0.49
    ar
    0.49
    newArrayList
    0.49
    BagLayout
    0.49
    Activations Density 0.682%

    No Known Activations