© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 10860
    Prev
    Next
    INDEX
    Explanations

    numeric values or sequences with specific formatting, likely related to measurements or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -1.14
     unknownFields
    -1.14
     saites
    -1.13
     itſelf
    -1.09
     uſed
    -1.05
    ]--;
    -1.04
     Roskov
    -1.01
     myſelf
    -1.00
    Geplaatst
    -0.99
     raiſ
    -0.99
    POSITIVE LOGITS
    ?
    0.58
    .
    0.50
     of
    0.50
     $\
    0.47
    $\
    0.47
    ...
    0.44
    ,
    0.44
    <strong>
    0.43
     a
    0.43
     in
    0.42
    Activations Density 0.355%

    No Known Activations