© 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. 8-GEMMASCOPE-RES-16K
    11. 15295
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or relationships in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bit
    -0.55
     genoux
    -0.54
    bayern
    -0.53
     azok
    -0.53
    toje
    -0.51
    ваний
    -0.50
     Looking
    -0.49
     bukan
    -0.49
     kapak
    -0.49
    فته
    -0.49
    POSITIVE LOGITS
     auquel
    1.16
    rungsseite
    1.00
    ]")]
    0.98
    __":
    0.96
     ThemeData
    0.93
     محفوظة
    0.93
     duquel
    0.92
    __':
    0.91
    клопе
    0.91
     WHICH
    0.89
    Activations Density 0.150%

    No Known Activations