© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2747
    Prev
    Next
    INDEX
    Explanations

    elements related to the structure and management of programming logic and data processing

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

    code-related tokens like current, temperature, and programming language constructs.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    tagHelperRunner
    -0.64
    FormTagHelper
    -0.63
    bcryptjs
    -0.59
    Personendaten
    -0.55
     Taktlose
    -0.54
    BufferException
    -0.54
     rumahnya
    -0.54
     queſto
    -0.53
     harganya
    -0.53
    antaranya
    -0.51
    POSITIVE LOGITS
    _
    0.46
    小
    0.43
     pseudo
    0.42
     Local
    0.42
    NumberOf
    0.41
     Real
    0.40
    EnableWeb
    0.40
     Saf
    0.39
    Local
    0.39
     مُعرِّف
    0.38
    Activations Density 0.344%

    No Known Activations