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 - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65851
    Prev
    Next
    INDEX
    Explanations

    the presence of file paths or directory structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAsync
    -0.49
    EDEFAULT
    -0.48
    AddTagHelper
    -0.45
    HtmlAttribute
    -0.45
     utafitiHapana
    -0.45
    期刊论文
    -0.41
    MarshalTo
    -0.41
     CreateTagHelper
    -0.41
    iettivo
    -0.41
    MigrationBuilder
    -0.41
    POSITIVE LOGITS
    msgTypes
    0.45
     esfuer
    0.44
    uxxxx
    0.43
     moderation
    0.43
     shop
    0.43
     mergeFrom
    0.42
    voerd
    0.42
    ostante
    0.42
    shop
    0.41
     rajut
    0.39
    Activations Density 0.003%

    No Known Activations