© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-GEMMASCOPE-RES-16K
    11. 4961
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to the concept of "formation" and the act of forming entities or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ennium
    -0.65
     itemView
    -0.56
    ographies
    -0.56
    Extractor
    -0.54
     Gres
    -0.54
     recenti
    -0.54
    ưỡi
    -0.54
     égard
    -0.54
    toByteArray
    -0.53
    wicz
    -0.53
    POSITIVE LOGITS
     formation
    1.69
     Formation
    1.64
     Forming
    1.62
     forming
    1.60
     formed
    1.59
     FORMATION
    1.58
    Formation
    1.46
     Formed
    1.44
     formations
    1.44
    formed
    1.28
    Activations Density 0.159%

    No Known Activations