© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 7813
    Prev
    Next
    INDEX
    Explanations

    information related to comparisons and alternatives

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

    implying something is "better"

    np_acts-logits-general · gemini-2.0-flash

    better alternative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstrumentedTest
    -0.49
    ClientSize
    -0.47
    cuencia
    -0.46
     acceptez
    -0.46
    BoxShadow
    -0.45
    opcao
    -0.45
    denas
    -0.42
     particolare
    -0.42
     Very
    -0.42
     Da
    -0.42
    POSITIVE LOGITS
     better
    1.50
    better
    1.40
    Better
    1.23
     BETTER
    1.18
     Better
    1.16
     preferable
    1.09
     bessere
    1.07
     bättre
    1.05
     besser
    1.05
     beter
    1.03
    Activations Density 0.412%

    No Known Activations