© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 384
    Prev
    Next
    INDEX
    Explanations

    conditional statements and terms associated with permissions or allowances

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

    uncertain or speculative language

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

    may be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     ✭✭
    -0.64
     AssemblyCompany
    -0.60
     Efq
    -0.59
    __*/
    -0.56
    ódz
    -0.53
     habet
    -0.51
    нциклопедия
    -0.51
    bleshooting
    -0.49
     „,
    -0.49
    Portály
    -0.48
    POSITIVE LOGITS
    andExpect
    0.65
     doInBackground
    0.64
     Audiodateien
    0.62
    AutoScaleMode
    0.61
    BorderFactory
    0.59
     InputDecoration
    0.58
    ...@
    0.56
    aternal
    0.55
     coinc
    0.55
    MessageOf
    0.55
    Activations Density 0.003%

    No Known Activations