© 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. 3-GEMMASCOPE-RES-16K
    11. 6261
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "the latter" in comparison to earlier mentioned items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\..\
    -0.48
    penta
    -0.46
     Jan
    -0.45
     anyways
    -0.44
     SIX
    -0.43
     kettle
    -0.43
     Rans
    -0.42
    creatic
    -0.41
     المعيارى
    -0.41
     JAN
    -0.41
    POSITIVE LOGITS
     latter
    0.75
     accelerated
    0.67
    Acceler
    0.66
    acceler
    0.66
     acceleration
    0.65
     beschleun
    0.65
     accelerating
    0.64
     accelerate
    0.63
     accél
    0.63
     Acceleration
    0.60
    Activations Density 0.080%

    No Known Activations