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. 2-GEMMASCOPE-RES-16K
    6. 15191
    Prev
    Next
    INDEX
    Explanations

    direct quotes or statements made by individuals

    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
    VersionUID
    -0.64
    fastjson
    -0.54
    skri
    -0.54
     oprot
    -0.53
    MinWidth
    -0.53
    siti
    -0.51
    teth
    -0.51
     CSRF
    -0.50
     hvil
    -0.49
    acic
    -0.49
    POSITIVE LOGITS
     says
    2.37
    Says
    2.17
    says
    2.15
     Says
    2.10
     SAYS
    1.80
     zegt
    1.41
     tells
    1.20
     säger
    1.18
     explains
    1.17
     sagt
    1.17
    Activations Density 0.093%

    No Known Activations