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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 2056
    Prev
    Next
    INDEX
    Explanations

    keywords related to structured data or object references, particularly those with coding or programming context

    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
     seção
    -0.55
    rungsseite
    -0.53
    فیلم
    -0.52
     linkovi
    -0.51
    crapers
    -0.51
     thương
    -0.50
    ipelago
    -0.50
    UnknownFieldSet
    -0.50
     cancell
    -0.49
    ท้าย
    -0.49
    POSITIVE LOGITS
    sw
    1.05
    sy
    1.02
    sa
    0.96
    sc
    0.93
    sp
    0.90
    sh
    0.87
    sm
    0.86
    sb
    0.85
    sd
    0.84
    sworth
    0.83
    Activations Density 0.194%

    No Known Activations