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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 4969
    Prev
    Next
    INDEX
    Explanations

    the concept of customization in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELTS
    -0.90
     KeyEvent
    -0.90
    ResumeLayout
    -0.89
     LoginComponent
    -0.88
    JFK
    -0.86
     MessageBoxIcon
    -0.85
    DockStyle
    -0.81
    <%=
    -0.81
     MenuView
    -0.80
     financeira
    -0.80
    POSITIVE LOGITS
     Custom
    1.60
     custom
    1.55
    custom
    1.52
    Custom
    1.47
    setCustom
    1.45
     CUSTOM
    1.34
     customized
    1.30
    CUSTOM
    1.24
     tailored
    1.15
     customised
    1.12
    Activations Density 0.063%

    No Known Activations