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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 196
    Prev
    Next
    INDEX
    Explanations

    legal terminologies and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     melibatkan
    -0.47
     polega
    -0.47
     serem
    -0.45
     constituyen
    -0.43
     получается
    -0.43
     afectan
    -0.41
     voltak
    -0.40
     resultan
    -0.39
     получится
    -0.38
    èches
    -0.38
    POSITIVE LOGITS
     has
    1.24
     took
    1.11
     had
    1.03
     will
    1.02
     knows
    0.99
     could
    0.94
     also
    0.94
     did
    0.94
     knew
    0.94
     wants
    0.93
    Activations Density 1.232%

    No Known Activations