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. 4-GEMMASCOPE-RES-16K
    6. 10949
    Prev
    Next
    INDEX
    Explanations

    code structure elements, particularly those related to function definitions and control flow statements

    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
    MemoryWarning
    -0.75
    SupportActionBar
    -0.74
    EndInit
    -0.71
    tvguidetime
    -0.67
     NSCoder
    -0.66
    PerformLayout
    -0.63
    HtmlAttribute
    -0.63
    RTDA
    -0.60
     שוליים
    -0.60
    ConstraintMaker
    -0.60
    POSITIVE LOGITS
    migrationBuilder
    0.66
     internationaux
    0.61
     chrétiens
    0.55
     vieill
    0.55
     chré
    0.54
     témoins
    0.53
     âgées
    0.53
     yeux
    0.51
     religieuses
    0.51
     internationales
    0.51
    Activations Density 0.063%

    No Known Activations