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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 2464
    Prev
    Next
    INDEX
    Explanations

    instances of the word "new"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelweddau
    -0.50
    ,
    -0.48
    5
    -0.44
    1
    -0.44
     she
    -0.43
    ;
    -0.43
    ...
    -0.43
    疏
    -0.43
    3
    -0.43
    ↵
    -0.42
    POSITIVE LOGITS
     CreateTagHelper
    1.01
    migrationBuilder
    1.00
    TagMode
    0.98
    __*/
    0.97
    CloseOperation
    0.96
    󠁢
    0.95
    Hentet
    0.94
    </thead>
    0.94
     autorytatywna
    0.92
     تضيفلها
    0.90
    Activations Density 0.011%

    No Known Activations