© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7239
    Prev
    Next
    INDEX
    Explanations

    elements related to form validation in web development

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

    Code snippets or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    code snippets and attributes

    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
    ########.
    -0.38
    mexic
    -0.33
     bulk
    -0.31
     sanitaires
    -0.30
     dune
    -0.30
     Buffalo
    -0.30
     rinse
    -0.29
     muni
    -0.29
     instead
    -0.28
     haste
    -0.28
    POSITIVE LOGITS
    ibatis
    0.69
    devamını
    0.66
    ftagPool
    0.66
     StringTokenizer
    0.60
    Condol
    0.60
    adaptiveStyles
    0.56
     "..\..\
    0.56
    djangoproject
    0.54
    tvguidetime
    0.53
    AndEndTag
    0.52
    Activations Density 0.328%

    No Known Activations