© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1944
    Prev
    Next
    INDEX
    Explanations

    phrases indicating examples or evidence of a claim

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
     jsPsych
    -0.32
    RegistryLite
    -0.32
     cold
    -0.31
     clutches
    -0.28
    partir
    -0.28
     relief
    -0.28
     холод
    -0.28
    uleiro
    -0.27
     stoff
    -0.27
     Cold
    -0.27
    POSITIVE LOGITS
     CreateTagHelper
    1.05
    iNdEx
    0.69
    󠁢
    0.65
     kuten
    0.63
     like
    0.63
    seperti
    0.60
     zoals
    0.60
    ﹠
    0.60
    <unused17>
    0.59
     Normdatei
    0.59
    Activations Density 0.485%

    No Known Activations