© 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. 2-GEMMASCOPE-RES-16K
    11. 994
    Prev
    Next
    INDEX
    Explanations

    references to press or media-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.76
     NgModule
    -0.69
    шру
    -0.65
    脚注の使い方
    -0.60
    Sneaky
    -0.58
     gutted
    -0.57
    Personendaten
    -0.57
    TypedDataSet
    -0.57
    alians
    -0.56
    polation
    -0.56
    POSITIVE LOGITS
     press
    3.74
     Press
    3.48
    Press
    3.41
    press
    3.40
     PRESS
    3.37
     presses
    2.98
    PRESS
    2.76
     pressed
    2.58
     presse
    2.53
     pressing
    2.46
    Activations Density 0.058%

    No Known Activations