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. 10-GEMMASCOPE-RES-16K
    6. 13339
    Prev
    Next
    INDEX
    Explanations

    terms related to legal violations and infringements of rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     modelAndView
    -0.64
    /******/
    -0.57
    codegen
    -0.56
    yeb
    -0.55
     بتاريخ
    -0.53
    EndContext
    -0.52
     online
    -0.52
     wild
    -0.51
     Brend
    -0.51
    гӀ
    -0.51
    POSITIVE LOGITS
     violate
    1.20
     violates
    1.18
     violated
    1.18
     violation
    1.17
     Violations
    1.14
     violations
    1.14
     Violation
    1.13
     Viol
    1.08
     Breach
    1.07
     violating
    1.03
    Activations Density 0.279%

    No Known Activations