© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 14664
    Prev
    Next
    INDEX
    Explanations

    information related to timing, delivery, or logistical details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.37
    了出去
    -0.37
    JsonInclude
    -0.36
     chodzi
    -0.35
    EndProject
    -0.34
    wnętr
    -0.34
     exposiciones
    -0.33
     recul
    -0.33
     expos
    -0.32
    migrationBuilder
    -0.32
    POSITIVE LOGITS
     arrive
    3.56
     arriving
    3.55
     arrived
    3.53
     arrival
    3.44
     arrives
    3.38
    Arri
    3.08
    arrive
    3.02
    arrived
    2.98
     Arri
    2.98
     Arrival
    2.97
    Activations Density 1.042%

    No Known Activations