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. 12-GEMMASCOPE-RES-16K
    6. 6512
    Prev
    Next
    INDEX
    Explanations

    the presence of the letter 'A' and various forms of it in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.99
    KommentareTeilen
    -0.94
    AddTagHelper
    -0.90
     muualla
    -0.89
    +#+#
    -0.87
     TextInputType
    -0.86
    principalTable
    -0.81
     Photocase
    -0.81
    gameserver
    -0.81
     ―――――
    -0.79
    POSITIVE LOGITS
     A
    1.28
    A
    1.05
    An
    0.77
     An
    0.76
     U
    0.71
     S
    0.69
     E
    0.68
    getA
    0.68
     F
    0.68
     C
    0.66
    Activations Density 0.279%

    No Known Activations