© 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. 20-GEMMASCOPE-RES-16K
    6. 10705
    Prev
    Next
    INDEX
    Explanations

    technical terminologies and programming concepts related to software installation and functionality

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

    answer-style and meta-structural cues from Stack Overflow–type Q&A posts (e.g., “A:”, updates, redirects to other questions, and solution statements).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.54
     mandatario
    -0.43
    +:+
    -0.42
    ądze
    -0.41
     gobernador
    -0.41
    AddTagHelper
    -0.41
     governador
    -0.40
    libft
    -0.38
     Tamaño
    -0.38
    setupUi
    -0.38
    POSITIVE LOGITS
    Хьажоргаш
    0.43
    rungsseite
    0.41
    ToProps
    0.41
     BoxFit
    0.41
     implicit
    0.41
     QI
    0.40
    obos
    0.40
     generalized
    0.40
     wikipedia
    0.40
    揄
    0.40
    Activations Density 1.212%

    No Known Activations