© 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. 35-GEMMASCOPE-RES-16K
    6. 6702
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and discussions surrounding possibilities and uncertainties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     either
    -0.80
     Either
    -0.74
    Either
    -0.71
    either
    -0.70
     instead
    -0.69
     malah
    -0.66
     even
    -0.65
    ITHER
    -0.60
     justru
    -0.60
    even
    -0.59
    POSITIVE LOGITS
     technically
    1.28
     nominally
    1.16
     theoretically
    1.09
    一見
    1.00
     ostensibly
    1.00
     téc
    1.00
     Technically
    0.96
     outwardly
    0.96
     admittedly
    0.94
    Technically
    0.94
    Activations Density 0.791%

    No Known Activations