© 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. 4-GEMMASCOPE-RES-16K
    11. 872
    Prev
    Next
    INDEX
    Explanations

    prominent names or terms related to individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.73
    '])
    -0.71
    ']);
    -0.66
    __":
    -0.66
    ]--;
    -0.65
    "];
    -0.64
    '])->
    -0.64
    __':
    -0.64
    "]];
    -0.63
    "])
    -0.63
    POSITIVE LOGITS
     photolibrary
    0.82
     myſelf
    0.79
    Capítulo
    0.77
     themſelves
    0.75
     CJK
    0.74
     ―――――
    0.74
     quæ
    0.72
     Efq
    0.72
     againſt
    0.71
     LXXX
    0.71
    Activations Density 2.108%

    No Known Activations