© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6230
    Prev
    Next
    INDEX
    Explanations

    phrases related to improving and increasing effectiveness in treatment strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.51
     latter
    -0.51
    l
    -0.46
     later
    -0.45
    <eos>
    -0.44
    </strong>
    -0.43
     -
    -0.43
     ok
    -0.42
     pourtant
    -0.42
     so
    -0.42
    POSITIVE LOGITS
     كومونز
    0.94
     Increase
    0.94
    Increase
    0.91
     increase
    0.90
     Increases
    0.86
    ICAGO
    0.86
     increases
    0.86
    increase
    0.84
    Increases
    0.83
    increases
    0.83
    Activations Density 0.324%

    No Known Activations