© 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. 15-GEMMASCOPE-RES-16K
    6. 5376
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to academic and clinical positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.46
     optique
    -0.45
     témoins
    -0.43
    小
    -0.41
     ши
    -0.41
     little
    -0.41
    ash
    -0.41
     décisions
    -0.40
     value
    -0.40
    alha
    -0.40
    POSITIVE LOGITS
    woordig
    0.85
    __":
    
    0.76
    __':
    
    0.75
    enumii
    0.75
    ########.
    0.73
    quartered
    0.72
    RTSC
    0.71
    zzleHttp
    0.71
    TestingModule
    0.69
     preſent
    0.68
    Activations Density 0.273%

    No Known Activations