© 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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 3993
    Prev
    Next
    INDEX
    Explanations

    identifiers and attributes related to files, modules, and versions in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasForeignKey
    -0.68
    Maße
    -0.66
    :+:
    -0.65
    FormTagHelper
    -0.64
    EDEFAULT
    -0.63
    RUnlock
    -0.63
    》.
    -0.63
    JvmStatic
    -0.63
    AccessFile
    -0.62
    ::~
    -0.62
    POSITIVE LOGITS
    GroupLayout
    1.56
    tagHelper
    1.33
    AutoScaleMode
    1.08
    fjspx
    0.84
    WithIOException
    0.82
     consultato
    0.82
    MessageBox
    0.82
    setVerticalGroup
    0.78
    UnknownFieldSet
    0.76
    mstyle
    0.69
    Activations Density 0.004%

    No Known Activations