© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 3706
    Prev
    Next
    INDEX
    Explanations

    sections of text that detail programming or technical structures and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    كتشاف
    -0.53
     vilá
    -0.52
     vux
    -0.49
    gines
    -0.48
     nærm
    -0.46
    cjach
    -0.46
     ausges
    -0.45
     medel
    -0.45
     okaz
    -0.45
    courage
    -0.44
    POSITIVE LOGITS
     للمعارف
    0.61
    ModelAdmin
    0.60
    NamedQueries
    0.59
    ariConfig
    0.58
     ADF
    0.57
    twimg
    0.57
    itev
    0.56
     mxArray
    0.56
    esModule
    0.55
    criminator
    0.55
    Activations Density 0.131%

    No Known Activations