© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15571
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the structure or organization of a document

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

    Text preceding "follows" or "shown"

    np_acts-logits-general · gemini-2.0-flash

    introducing lists or explanations

    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
    InlineData
    -0.56
    Somehow
    -0.53
    Portail
    -0.52
     dagegen
    -0.51
    =?,
    -0.50
     Somehow
    -0.48
     andererseits
    -0.47
    geschenk
    -0.47
    kto
    -0.47
    openConnection
    -0.46
    POSITIVE LOGITS
     following
    2.41
     follows
    2.27
    following
    2.13
     follow
    1.97
     Following
    1.97
    Following
    1.84
    follows
    1.81
    follow
    1.69
     FOLLOWING
    1.68
     Follows
    1.62
    Activations Density 0.327%

    No Known Activations