© 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. 18-GEMMASCOPE-RES-16K
    11. 15269
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "base" or "baseline" in various contexts

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

    The token "base"

    np_acts-logits-general · gemini-2.0-flash

    technical contexts around base

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.68
     NSCoder
    -0.66
     useAppContext
    -0.64
    ArrowToggle
    -0.63
     betweenstory
    -0.63
     récomp
    -0.60
    JSONException
    -0.59
     proprement
    -0.58
     onCreateView
    -0.57
    utilisons
    -0.56
    POSITIVE LOGITS
     BASE
    0.90
     Base
    0.88
     getBase
    0.84
     BAS
    0.81
     base
    0.79
    BASE
    0.78
    Bases
    0.76
    bases
    0.76
    BAS
    0.74
    base
    0.73
    Activations Density 0.159%

    No Known Activations