Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 6159
    Prev
    Next
    INDEX
    Explanations

    variations and occurrences of the sequence "AA" 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 @ 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
    WithIOException
    -0.87
     تضيفلها
    -0.87
    sidemargin
    -0.72
    StoryboardSegue
    -0.66
     Wicidata
    -0.66
    Personensuche
    -0.66
    EndProject
    -0.65
    دانشنامهٔ
    -0.64
    latz
    -0.64
     PUL
    -0.63
    POSITIVE LOGITS
    AA
    3.73
     AA
    3.16
    aa
    2.46
     aa
    2.00
    AAA
    1.98
     AAA
    1.74
    AAAA
    1.63
    Aa
    1.43
    AAAAAA
    1.35
     Aa
    1.35
    Activations Density 0.052%

    No Known Activations