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-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5835
    Prev
    Next
    INDEX
    Explanations

    terms related to health regulations and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    magitan
    -0.68
     desmotivaciones
    -0.68
     muchacha
    -0.65
    gucig
    -0.65
     auroit
    -0.62
    OGND
    -0.60
     määrä
    -0.60
    ambién
    -0.60
     étoit
    -0.59
     saveiro
    -0.58
    POSITIVE LOGITS
    /**
    0.47
     Мексичка
    0.42
     Италијани
    0.38
    цездатний
    0.36
     resourceCulture
    0.36
    /*
    0.34
     <=",
    0.34
     lenker
    0.33
    <bos>
    0.31
    лтамалар
    0.30
    Activations Density 1.109%

    No Known Activations