Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 13330
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures and their associated risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.80
    matchCondition
    -0.79
    DockStyle
    -0.77
    mybatisplus
    -0.75
    principalColumn
    -0.73
    IntoConstraints
    -0.68
    AndEndTag
    -0.67
     ProtoMessage
    -0.66
     HasFactory
    -0.65
     bezeichneter
    -0.65
    POSITIVE LOGITS
     custom
    0.52
     services
    0.50
    gms
    0.43
     }
    0.42
      
    0.40
     software
    0.40
     optionally
    0.38
     egent
    0.38
    Soft
    0.38
    Iné
    0.38
    Activations Density 0.252%

    No Known Activations