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

    Neuronpedia

    Jacobian LensNEW
    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 - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4885
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and scripting functions

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

    Tokens preceding actions or consequences

    np_acts-logits-general · gemini-2.0-flash

    automatic actions and detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marginHorizontal
    -0.63
    orda
    -0.42
     rời
    -0.42
     tritt
    -0.41
     experimenter
    -0.40
    杵
    -0.40
    MockMvc
    -0.40
     Mudah
    -0.40
     clinica
    -0.40
     Malte
    -0.40
    POSITIVE LOGITS
     automatically
    1.42
     Automatically
    1.16
    automatically
    1.14
     detect
    1.12
     automatiquement
    1.11
     detects
    1.09
     automaticamente
    1.03
     detecting
    1.01
     auto
    1.00
     intelligently
    0.99
    Activations Density 0.722%

    No Known Activations