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. 33-GEMMASCOPE-RES-16K
    6. 11210
    Prev
    Next
    INDEX
    Explanations

    actions related to research methodology and experimental analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    fromnode
    -0.50
     Autorizaciones
    -0.48
     betweenstory
    -0.46
     AppCompatTheme
    -0.46
    دانشنامهٔ
    -0.45
     AssemblyProduct
    -0.44
    kusen
    -0.43
    specie
    -0.40
    AddHtmlAttribute
    -0.39
    MigrationBuilder
    -0.39
    POSITIVE LOGITS
    Diweddarwch
    0.48
    Tikang
    0.47
     whereby
    0.44
    Personensuche
    0.43
     CreateTagHelper
    0.42
    ResponseWriter
    0.42
    Xna
    0.41
    Erreferentziak
    0.41
    ########.
    0.41
    msleep
    0.41
    Activations Density 0.964%

    No Known Activations