© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 3261
    Prev
    Next
    INDEX
    Explanations

    discussions related to education and training events

    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
    PyObject
    -0.42
     препратки
    -0.37
    ultas
    -0.35
    geslacht
    -0.33
    erokee
    -0.33
    xase
    -0.33
    TestBed
    -0.32
    RTEX
    -0.32
    ObjectContext
    -0.31
    ExecutionContext
    -0.31
    POSITIVE LOGITS
     worldwide
    2.59
     nationwide
    2.39
     globally
    2.28
    worldwide
    2.23
     everywhere
    2.03
     across
    2.03
     nationally
    2.03
     weltweit
    1.88
    Worldwide
    1.86
     internationally
    1.83
    Activations Density 1.481%

    No Known Activations