Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 6020
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenges or obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mess
    -0.58
    ACTS
    -0.54
    issner
    -0.53
     weg
    -0.53
     Blak
    -0.52
    FOLIO
    -0.50
    onges
    -0.49
    落
    -0.49
    лас
    -0.48
    usser
    -0.48
    POSITIVE LOGITS
     difficulty
    3.39
    difficulty
    3.05
     Difficulty
    2.96
    Difficulty
    2.48
     difficulties
    2.30
     Difficulties
    2.26
     dificultad
    2.12
     difficoltà
    1.99
     difficulté
    1.96
    diffic
    1.93
    Activations Density 0.082%

    No Known Activations