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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1501
    Prev
    Next
    INDEX
    Explanations

    terms related to experimental data and validation in scientific research

    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
     nahilalakip
    -0.49
    providedIn
    -0.40
    astéro
    -0.38
    ViewFeatures
    -0.38
     supone
    -0.36
    tagext
    -0.36
     teórico
    -0.35
     normalidad
    -0.34
     playera
    -0.34
    enschappelijke
    -0.33
    POSITIVE LOGITS
    Hentet
    0.59
     factual
    0.56
    observed
    0.53
    empi
    0.53
     facts
    0.53
    actual
    0.52
     Observed
    0.51
    /**
    0.51
    Actual
    0.50
    EndGlobalSection
    0.49
    Activations Density 1.480%

    No Known Activations