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. 13-GEMMASCOPE-RES-16K
    6. 12541
    Prev
    Next
    INDEX
    Explanations

    topics related to analysis of systems and their possible improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.58
    ($__
    -0.52
     VizieR
    -0.48
    atste
    -0.45
    DockStyle
    -0.45
    unción
    -0.44
     trasc
    -0.42
    usercontent
    -0.42
    urlopen
    -0.41
    extField
    -0.40
    POSITIVE LOGITS
    Ideally
    0.78
     preferably
    0.77
    preferably
    0.77
     should
    0.77
     Should
    0.74
     ideally
    0.74
     Ideally
    0.73
    Shouldn
    0.72
    Should
    0.72
     sorely
    0.71
    Activations Density 0.610%

    No Known Activations