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. 22-GEMMASCOPE-RES-16K
    6. 13859
    Prev
    Next
    INDEX
    Explanations

    code snippets related to programming and functions in C++

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

    C/C++ code and header information

    np_acts-logits-general · gemini-2.0-flash

    C/C++ code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,:]
    -0.62
     (;;)
    -0.56
     volar
    -0.54
    },[
    -0.49
    bele
    -0.48
    RING
    -0.48
    [:,:,
    -0.47
    MLLoader
    -0.47
    eles
    -0.47
     übers
    -0.47
    POSITIVE LOGITS
    ########.
    1.23
    :+:
    1.01
    libft
    0.98
    ft
    0.81
     ft
    0.79
    +#+
    0.75
    mlx
    0.66
     kasarigan
    0.66
    #+#
    0.66
     referenties
    0.64
    Activations Density 0.040%

    No Known Activations