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. 9-GEMMASCOPE-RES-16K
    6. 9226
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "come" and its related forms or derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pap
    -0.54
     ((
    -0.53
    <sup>
    -0.52
     (
    -0.52
     sert
    -0.51
     It
    -0.50
     There
    -0.50
     
    -0.50
    πό
    -0.49
    *((
    -0.49
    POSITIVE LOGITS
    ########.
    1.10
    SharedDtor
    1.06
     rospy
    1.01
    WebVitals
    1.00
    PerformLayout
    0.97
    SPATH
    0.92
    rizona
    0.91
    TintMode
    0.89
     snippetHide
    0.88
    »։
    0.87
    Activations Density 0.101%

    No Known Activations