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. 6-GEMMASCOPE-RES-16K
    6. 5218
    Prev
    Next
    INDEX
    Explanations

    the letter "A" in various formats and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the letter "A" at the beginning of text passages.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -1.01
    Autoritní
    -1.01
    Tikang
    -0.96
    transQ
    -0.91
     Kamer
    -0.91
     незавершена
    -0.91
    adpleegd
    -0.90
     Signalez
    -0.89
     TextInputType
    -0.88
    +#+#
    -0.87
    POSITIVE LOGITS
     A
    1.91
    A
    1.82
    getA
    1.28
    А
    1.10
    An
    1.10
    tA
    1.09
     А
    1.05
    nA
    1.03
     An
    1.01
    pA
    0.94
    Activations Density 0.224%

    No Known Activations