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. 13082
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and interactions involving "you" and "me."

    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
    OGND
    -0.59
    हाय
    -0.57
     marinho
    -0.56
     TTS
    -0.55
     notifying
    -0.54
     terang
    -0.54
    valget
    -0.53
    raszam
    -0.53
     Schmuck
    -0.53
    ArgsConstructor
    -0.52
    POSITIVE LOGITS
    Gimme
    0.85
     a
    0.76
    awtextra
    0.74
    ]>=
    0.72
    DockStyle
    0.71
    mutable
    0.68
    given
    0.68
    oneofs
    0.68
    insee
    0.67
     Take
    0.67
    Activations Density 0.132%

    No Known Activations