© 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. 18-GEMMASCOPE-RES-16K
    6. 11677
    Prev
    Next
    INDEX
    Explanations

    details about individuals' professional backgrounds and accomplishments

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

    Following "also," "and," or similar conjunctions

    np_acts-logits-general · gemini-2.0-flash

    teaching, lecturing, and training

    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
    TypedDataSet
    -0.60
    lotten
    -0.55
    COUVER
    -0.50
    AddTagHelper
    -0.50
     חיצוניים
    -0.48
    Chham
    -0.47
    qrstuvwxyz
    -0.46
     smart
    -0.45
    ])]
    -0.43
    సు
    -0.42
    POSITIVE LOGITS
     teaching
    1.41
     lecturing
    1.23
    teaching
    1.20
     Teaching
    1.12
    Teaching
    1.11
     coaching
    1.11
     teach
    1.10
     mengajar
    1.03
     TEACHING
    1.01
     consultancy
    0.99
    Activations Density 0.328%

    No Known Activations