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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12-GEMMASCOPE-RES-16K
    6. 947
    Prev
    Next
    INDEX
    Explanations

    expressions of intention and making plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UDC
    -0.49
     ép
    -0.46
     Junge
    -0.46
     vo
    -0.44
     Dream
    -0.44
    GCM
    -0.43
     eigentlich
    -0.43
    GREES
    -0.42
    amentos
    -0.42
    Master
    -0.42
    POSITIVE LOGITS
     متعلقه
    0.99
     Infórmanos
    0.84
    WriteTagHelper
    0.77
    UseVisualStyle
    0.75
    makeText
    0.75
    mybatisplus
    0.72
    setViewportView
    0.68
    enderror
    0.68
    nestjs
    0.66
    BASEPATH
    0.66
    Activations Density 0.170%

    No Known Activations