© 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. 16130
    Prev
    Next
    INDEX
    Explanations

    citations and references related to research studies

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

    Citations or references using square brackets

    np_acts-logits-general · gemini-2.0-flash

    citations and references

    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
    stateProvider
    -0.58
     grandchildren
    -0.56
    帖最后由
    -0.55
    SizeF
    -0.52
    ":"",
    -0.52
    曖昧さ回避
    -0.51
     autorytatywna
    -0.51
    startAnimation
    -0.49
    RoutingModule
    -0.49
     TAMBIÉN
    -0.49
    POSITIVE LOGITS
    reviewed
    0.78
    refs
    0.67
     Refs
    0.65
    Refs
    0.61
    unpublished
    0.60
     refs
    0.57
    ref
    0.54
     보고
    0.52
    styleable
    0.52
    see
    0.52
    Activations Density 0.419%

    No Known Activations