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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 756
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and technical terms related to programming and digital content

    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
     незавершена
    -0.80
     Waray
    -0.68
     AssemblyCulture
    -0.66
     BIBSYS
    -0.61
     Efq
    -0.60
    bbene
    -0.60
    enoord
    -0.58
     InputDecoration
    -0.58
    sidemargin
    -0.57
    BibitemShut
    -0.57
    POSITIVE LOGITS
    pod
    0.58
     Butter
    0.58
    .(*
    0.57
    SequentialGroup
    0.56
     Bureau
    0.55
     butter
    0.55
     pod
    0.55
    ub
    0.53
    tgz
    0.53
     bureau
    0.51
    Activations Density 2.423%

    No Known Activations