© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12878
    Prev
    Next
    INDEX
    Explanations

    references to specific programming constructs or syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.71
    Portail
    -0.68
    Autoritní
    -0.64
     onBind
    -0.62
     незавершена
    -0.61
    +#+#
    -0.58
    #+#
    -0.57
     Nine
    -0.52
     виправивши
    -0.51
    ContentAsync
    -0.51
    POSITIVE LOGITS
     Chwiliwch
    0.57
     ten
    0.56
     fifteen
    0.53
    Whilst
    0.52
     Whilst
    0.52
     twelve
    0.49
     fourteen
    0.48
     eleven
    0.44
     fifty
    0.43
     gastronomía
    0.42
    Activations Density 0.165%

    No Known Activations