© 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. 17-GEMMASCOPE-RES-16K
    6. 9320
    Prev
    Next
    INDEX
    Explanations

    discussions around financial implications and investments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hauptartikel
    -0.56
    ∮
    -0.53
    kuuta
    -0.51
    awtextra
    -0.46
    MouseAdapter
    -0.46
    createCanvas
    -0.45
    Power
    -0.45
    featureID
    -0.44
    Quoi
    -0.43
     }}"></
    -0.42
    POSITIVE LOGITS
     ROI
    1.28
     profitability
    1.22
     recoup
    1.17
     payback
    1.16
     amorti
    1.09
     profit
    1.06
     cost
    0.98
     justify
    0.96
     profitable
    0.96
     Profit
    0.96
    Activations Density 0.231%

    No Known Activations