© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4586
    Prev
    Next
    INDEX
    Explanations

    questions regarding coding, programming help, and job-related inquiries in the tech field

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

    computer programming

    np_acts-logits-general · gemini-2.0-flash

    programming and development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sisält
    -0.41
    期刊论文
    -0.40
    ilitary
    -0.40
     llorar
    -0.40
     služ
    -0.38
     mandatario
    -0.38
     zarar
    -0.38
     disfruta
    -0.37
    gsSP
    -0.37
     prés
    -0.36
    POSITIVE LOGITS
     programming
    1.23
     Programming
    1.16
     coding
    1.16
     Python
    1.12
     coder
    1.10
     programmer
    1.07
     programmers
    1.06
     code
    1.06
    Programming
    1.04
     Coding
    1.03
    Activations Density 2.235%

    No Known Activations