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. 15-GEMMASCOPE-RES-16K
    6. 1682
    Prev
    Next
    INDEX
    Explanations

    actions of leaving or fleeing from situations

    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
    +:+
    -0.72
    utiny
    -0.62
    marshaller
    -0.61
    OGND
    -0.59
    Còn
    -0.58
    học
    -0.58
     sesama
    -0.57
    BeginInit
    -0.56
    IndentedString
    -0.55
     gepubliceerd
    -0.54
    POSITIVE LOGITS
     completely
    0.77
     away
    0.63
     totally
    0.63
    IsContent
    0.63
    completely
    0.62
     entirely
    0.60
     Completely
    0.58
    tagHelperRunner
    0.57
    fjspx
    0.55
     utterly
    0.55
    Activations Density 0.320%

    No Known Activations