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. 18-GEMMASCOPE-RES-16K
    6. 3095
    Prev
    Next
    INDEX
    Explanations

    terms related to severity and intensity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    degree or strength

    np_acts-logits-general · gemini-2.0-flash

    strength and intensity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    قایناقلار
    -0.54
    ItemBackground
    -0.51
     Wikimedijinoj
    -0.48
    enumi
    -0.47
     OFDb
    -0.47
    viale
    -0.46
    اریخ
    -0.46
    getRuntime
    -0.45
    onomía
    -0.45
     rischio
    -0.44
    POSITIVE LOGITS
     intensity
    1.67
     strength
    1.61
     stronger
    1.52
    strength
    1.49
     Intensity
    1.46
     strongest
    1.35
    intensity
    1.34
     strong
    1.31
     intensities
    1.31
    Intensity
    1.30
    Activations Density 0.855%

    No Known Activations