Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1532
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific and technical concepts, particularly in the fields of medicine and physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fsen
    -0.58
    ParallelGroup
    -0.53
    Бахар
    -0.51
     BorderRadius
    -0.48
    AddRange
    -0.47
    cillor
    -0.46
    lech
    -0.46
     bezeichneter
    -0.46
     prostřed
    -0.44
     thereafter
    -0.44
    POSITIVE LOGITS
     Италијани
    0.44
    principalColumn
    0.44
    ChildScrollView
    0.44
     CanadaChoose
    0.44
     HasFactory
    0.39
    MessageTagHelper
    0.37
    /**
    0.36
    XmlEnum
    0.35
     jspb
    0.35
    /*
    0.35
    Activations Density 0.593%

    No Known Activations