© 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. 1-GEMMASCOPE-RES-16K
    6. 10624
    Prev
    Next
    INDEX
    Explanations

    instances of the word "da" and its variations, which likely indicates a focus on repeated or important terms in the dataset

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }{@
    -0.67
    itek
    -0.62
     Tiong
    -0.59
    mensch
    -0.58
     ModelExpression
    -0.58
    ſtance
    -0.56
    }$​
    -0.55
    epar
    -0.54
    isseau
    -0.54
    ſy
    -0.54
    POSITIVE LOGITS
    da
    3.71
    DA
    3.13
    Da
    2.66
     DA
    2.55
     Da
    2.54
     da
    2.47
    daj
    1.43
    dah
    1.40
    daa
    1.39
    das
    1.36
    Activations Density 0.039%

    No Known Activations