© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1940
    Prev
    Next
    INDEX
    Explanations

    phrases related to case studies and reports

    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
     Monfieur
    -1.06
     Eſ
    -0.99
     Efq
    -0.96
    ]--;
    -0.90
     كورة
    -0.88
     Theſe
    -0.87
     itſelf
    -0.86
    VIAF
    -0.85
    ruptedException
    -0.85
     myſelf
    -0.84
    POSITIVE LOGITS
     case
    2.21
     Case
    2.09
    Case
    2.03
    case
    1.97
     cases
    1.92
     Cases
    1.84
     CASE
    1.79
    CASE
    1.71
    Cases
    1.71
     caso
    1.66
    Activations Density 0.309%

    No Known Activations