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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1888
    Prev
    Next
    INDEX
    Explanations

    URLs and web links associated with GitHub and Google

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

    URLs from GitHub

    np_acts-logits-general · gemini-2.0-flash

    github repository links

    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
    ngdoc
    -0.81
     propOrder
    -0.70
     SafeMath
    -0.64
     HasFactory
    -0.62
    +#+#
    -0.62
    FormTagHelper
    -0.62
     InputDecoration
    -0.62
     <<<<<<<<<<<<<<
    -0.61
    >');
    -0.59
     mxArray
    -0.57
    POSITIVE LOGITS
    usercontent
    0.54
    rapie
    0.48
    mosis
    0.48
    /@
    0.47
     ArrayAdapter
    0.46
    setImageBitmap
    0.45
    _/
    0.42
    /
    0.42
     paso
    0.42
     naman
    0.41
    Activations Density 0.089%

    No Known Activations