© 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. 2-GEMMASCOPE-RES-16K
    11. 15252
    Prev
    Next
    INDEX
    Explanations

    function pointer syntax and method calls in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -0.69
     Jacobs
    -0.59
     Jan
    -0.57
     I
    -0.55
     Gron
    -0.54
     l
    -0.53
     Sal
    -0.51
     in
    -0.51
     sal
    -0.51
     περι
    -0.50
    POSITIVE LOGITS
    )->
    2.52
    ")->
    2.42
    ]->
    2.20
    ))->
    2.15
    ])->
    1.90
    ())->
    1.86
    ')->
    1.86
    ->
    1.75
    })->
    1.75
    '])->
    1.69
    Activations Density 0.132%

    No Known Activations