© 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. 2-GEMMASCOPE-RES-16K
    11. 3941
    Prev
    Next
    INDEX
    Explanations

    sentences ending with punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     temprano
    -0.57
     lancement
    -0.57
     refroid
    -0.57
    StoryboardSegue
    -0.55
     démarrage
    -0.54
    Autoritní
    -0.54
     feroit
    -0.53
     auroit
    -0.53
     lendemain
    -0.52
     isInitialized
    -0.51
    POSITIVE LOGITS
     amen
    0.48
    小松
    0.47
     irri
    0.46
    PyObject
    0.45
     ?>">
    0.45
     ['$
    0.44
    ">{{$
    0.43
     anatom
    0.43
    esez
    0.42
     "
    0.42
    Activations Density 0.029%

    No Known Activations