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. 3-GEMMASCOPE-RES-16K
    6. 10074
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to events or performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.70
    — 
    -0.63
     виправивши
    -0.62
     Bris
    -0.60
     Exactos
    -0.58
    verwijspagina
    -0.57
    bomb
    -0.56
    ніципалі
    -0.56
     Jef
    -0.55
     PublicKey
    -0.55
    POSITIVE LOGITS
    afone
    0.59
    stretchr
    0.58
     Audiodateien
    0.57
    bcryptjs
    0.56
     scolaires
    0.55
    MessageOf
    0.54
    JsonFormat
    0.51
     naturen
    0.51
     šir
    0.51
     artistique
    0.51
    Activations Density 0.036%

    No Known Activations