© 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. 24-GEMMASCOPE-RES-16K
    6. 4079
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mathematical concepts and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical groups and root systems

    np_acts-logits-general · gemini-2.0-flash

    Lie groups and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibatis
    -0.60
    TagHelpers
    -0.58
    requestCode
    -0.57
    URLException
    -0.53
    tagHelper
    -0.52
     Pust
    -0.51
    apunov
    -0.51
    createCanvas
    -0.50
    readystatechange
    -0.50
    TSCA
    -0.50
    POSITIVE LOGITS
     group
    0.75
    FormTagHelper
    0.69
     subgroup
    0.67
    group
    0.65
     groups
    0.63
     grupo
    0.62
     csoport
    0.61
     subgroups
    0.61
     groupes
    0.60
     Lie
    0.59
    Activations Density 1.052%

    No Known Activations