© 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. 24-GEMMASCOPE-RES-16K
    6. 14868
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and research findings

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

    That something is needed

    np_acts-logits-general · gemini-2.0-flash

    calls for research or evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagHelper
    -0.53
     كومونز
    -0.51
    IVEREF
    -0.51
    ReturnValue
    -0.49
     linkovi
    -0.49
    êcher
    -0.49
    StoryboardSegue
    -0.48
    ोंने
    -0.48
    styleType
    -0.48
    MessageTagHelper
    -0.48
    POSITIVE LOGITS
     needed
    3.16
     required
    3.10
     necessary
    2.88
    needed
    2.67
    required
    2.65
     Needed
    2.57
     Required
    2.50
    necessary
    2.43
    Required
    2.42
    Needed
    2.31
    Activations Density 0.673%

    No Known Activations