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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 2792
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Mar" followed by a number, indicating dates or references to the month of March

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.51
    OGND
    -0.50
    ">//
    -0.41
    slidesPer
    -0.41
    TextHelper
    -0.38
     plomb
    -0.37
    MessageTagHelper
    -0.36
    IBarButtonItem
    -0.36
    Demografie
    -0.34
    FixedSize
    -0.34
    POSITIVE LOGITS
     ffilmiau
    0.49
     surla
    0.47
    matchCondition
    0.44
    mot
    0.42
    XmlAccessorType
    0.41
    rying
    0.40
    verwijspagina
    0.40
     abstrait
    0.39
     rationale
    0.38
     Lightboxes
    0.38
    Activations Density 0.308%

    No Known Activations